Author: mikej Date: Mon Jun 8 18:51:30 2009 New Revision: 13706 Log: update to pcre 7.9 Added: freeswitch/trunk/libs/pcre/132html (contents, props changed) freeswitch/trunk/libs/pcre/CleanTxt (contents, props changed) freeswitch/trunk/libs/pcre/Detrail (contents, props changed) freeswitch/trunk/libs/pcre/HACKING freeswitch/trunk/libs/pcre/Makefile.am freeswitch/trunk/libs/pcre/PrepareRelease (contents, props changed) freeswitch/trunk/libs/pcre/RunTest.bat freeswitch/trunk/libs/pcre/cmake/ freeswitch/trunk/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS freeswitch/trunk/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake freeswitch/trunk/libs/pcre/cmake/FindReadline.cmake freeswitch/trunk/libs/pcre/config-cmake.h.in freeswitch/trunk/libs/pcre/config.h.generic freeswitch/trunk/libs/pcre/depcomp (contents, props changed) freeswitch/trunk/libs/pcre/doc/html/pcre-config.html freeswitch/trunk/libs/pcre/doc/html/pcresyntax.html freeswitch/trunk/libs/pcre/doc/index.html.src freeswitch/trunk/libs/pcre/doc/pcre-config.1 freeswitch/trunk/libs/pcre/doc/pcre-config.txt freeswitch/trunk/libs/pcre/doc/pcresyntax.3 freeswitch/trunk/libs/pcre/libpcrecpp.pc.in freeswitch/trunk/libs/pcre/makevp_c.txt freeswitch/trunk/libs/pcre/makevp_l.txt freeswitch/trunk/libs/pcre/pcre.h.generic freeswitch/trunk/libs/pcre/pcre.h.in freeswitch/trunk/libs/pcre/pcre_chartables.c.dist freeswitch/trunk/libs/pcre/pcre_newline.c freeswitch/trunk/libs/pcre/pcre_ucd.c freeswitch/trunk/libs/pcre/pcrecpp_internal.h freeswitch/trunk/libs/pcre/pcregexp.pas freeswitch/trunk/libs/pcre/perltest.pl (contents, props changed) freeswitch/trunk/libs/pcre/testdata/grepinput8 freeswitch/trunk/libs/pcre/testdata/grepinputv freeswitch/trunk/libs/pcre/testdata/grepoutput8 freeswitch/trunk/libs/pcre/testdata/grepoutputN freeswitch/trunk/libs/pcre/testdata/testinput10 freeswitch/trunk/libs/pcre/testdata/testoutput10 freeswitch/trunk/libs/pcre/testdata/wintestinput3 freeswitch/trunk/libs/pcre/testdata/wintestoutput3 Modified: freeswitch/trunk/libs/pcre/AUTHORS freeswitch/trunk/libs/pcre/CMakeLists.txt freeswitch/trunk/libs/pcre/COPYING freeswitch/trunk/libs/pcre/ChangeLog freeswitch/trunk/libs/pcre/INSTALL freeswitch/trunk/libs/pcre/LICENCE freeswitch/trunk/libs/pcre/Makefile.in freeswitch/trunk/libs/pcre/NEWS freeswitch/trunk/libs/pcre/NON-UNIX-USE freeswitch/trunk/libs/pcre/README freeswitch/trunk/libs/pcre/config.h.in freeswitch/trunk/libs/pcre/configure.ac freeswitch/trunk/libs/pcre/dftables.c freeswitch/trunk/libs/pcre/doc/html/index.html freeswitch/trunk/libs/pcre/doc/html/pcre.html freeswitch/trunk/libs/pcre/doc/html/pcre_compile.html freeswitch/trunk/libs/pcre/doc/html/pcre_compile2.html freeswitch/trunk/libs/pcre/doc/html/pcre_config.html freeswitch/trunk/libs/pcre/doc/html/pcre_copy_substring.html freeswitch/trunk/libs/pcre/doc/html/pcre_dfa_exec.html freeswitch/trunk/libs/pcre/doc/html/pcre_exec.html freeswitch/trunk/libs/pcre/doc/html/pcre_fullinfo.html freeswitch/trunk/libs/pcre/doc/html/pcre_get_named_substring.html freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringnumber.html freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringtable_entries.html freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring.html freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring_list.html freeswitch/trunk/libs/pcre/doc/html/pcreapi.html freeswitch/trunk/libs/pcre/doc/html/pcrebuild.html freeswitch/trunk/libs/pcre/doc/html/pcrecallout.html freeswitch/trunk/libs/pcre/doc/html/pcrecompat.html freeswitch/trunk/libs/pcre/doc/html/pcrecpp.html freeswitch/trunk/libs/pcre/doc/html/pcregrep.html freeswitch/trunk/libs/pcre/doc/html/pcrematching.html freeswitch/trunk/libs/pcre/doc/html/pcrepartial.html freeswitch/trunk/libs/pcre/doc/html/pcrepattern.html freeswitch/trunk/libs/pcre/doc/html/pcreperform.html freeswitch/trunk/libs/pcre/doc/html/pcreposix.html freeswitch/trunk/libs/pcre/doc/html/pcreprecompile.html freeswitch/trunk/libs/pcre/doc/html/pcresample.html freeswitch/trunk/libs/pcre/doc/html/pcrestack.html freeswitch/trunk/libs/pcre/doc/html/pcretest.html freeswitch/trunk/libs/pcre/doc/pcre.3 freeswitch/trunk/libs/pcre/doc/pcre.txt freeswitch/trunk/libs/pcre/doc/pcre_compile.3 freeswitch/trunk/libs/pcre/doc/pcre_compile2.3 freeswitch/trunk/libs/pcre/doc/pcre_config.3 freeswitch/trunk/libs/pcre/doc/pcre_copy_named_substring.3 freeswitch/trunk/libs/pcre/doc/pcre_copy_substring.3 freeswitch/trunk/libs/pcre/doc/pcre_dfa_exec.3 freeswitch/trunk/libs/pcre/doc/pcre_exec.3 freeswitch/trunk/libs/pcre/doc/pcre_free_substring.3 freeswitch/trunk/libs/pcre/doc/pcre_free_substring_list.3 freeswitch/trunk/libs/pcre/doc/pcre_fullinfo.3 freeswitch/trunk/libs/pcre/doc/pcre_get_named_substring.3 freeswitch/trunk/libs/pcre/doc/pcre_get_stringnumber.3 freeswitch/trunk/libs/pcre/doc/pcre_get_stringtable_entries.3 freeswitch/trunk/libs/pcre/doc/pcre_get_substring.3 freeswitch/trunk/libs/pcre/doc/pcre_get_substring_list.3 freeswitch/trunk/libs/pcre/doc/pcre_info.3 freeswitch/trunk/libs/pcre/doc/pcre_maketables.3 freeswitch/trunk/libs/pcre/doc/pcre_refcount.3 freeswitch/trunk/libs/pcre/doc/pcre_study.3 freeswitch/trunk/libs/pcre/doc/pcre_version.3 freeswitch/trunk/libs/pcre/doc/pcreapi.3 freeswitch/trunk/libs/pcre/doc/pcrebuild.3 freeswitch/trunk/libs/pcre/doc/pcrecallout.3 freeswitch/trunk/libs/pcre/doc/pcrecompat.3 freeswitch/trunk/libs/pcre/doc/pcrecpp.3 freeswitch/trunk/libs/pcre/doc/pcregrep.1 freeswitch/trunk/libs/pcre/doc/pcregrep.txt freeswitch/trunk/libs/pcre/doc/pcrematching.3 freeswitch/trunk/libs/pcre/doc/pcrepartial.3 freeswitch/trunk/libs/pcre/doc/pcrepattern.3 freeswitch/trunk/libs/pcre/doc/pcreperform.3 freeswitch/trunk/libs/pcre/doc/pcreposix.3 freeswitch/trunk/libs/pcre/doc/pcreprecompile.3 freeswitch/trunk/libs/pcre/doc/pcresample.3 freeswitch/trunk/libs/pcre/doc/pcrestack.3 freeswitch/trunk/libs/pcre/doc/pcretest.1 freeswitch/trunk/libs/pcre/doc/pcretest.txt freeswitch/trunk/libs/pcre/libpcre.pc.in freeswitch/trunk/libs/pcre/makevp.bat freeswitch/trunk/libs/pcre/pcre-config.in freeswitch/trunk/libs/pcre/pcre.h freeswitch/trunk/libs/pcre/pcre_compile.c freeswitch/trunk/libs/pcre/pcre_config.c freeswitch/trunk/libs/pcre/pcre_dfa_exec.c freeswitch/trunk/libs/pcre/pcre_exec.c freeswitch/trunk/libs/pcre/pcre_fullinfo.c freeswitch/trunk/libs/pcre/pcre_get.c freeswitch/trunk/libs/pcre/pcre_globals.c freeswitch/trunk/libs/pcre/pcre_info.c freeswitch/trunk/libs/pcre/pcre_internal.h freeswitch/trunk/libs/pcre/pcre_maketables.c freeswitch/trunk/libs/pcre/pcre_ord2utf8.c freeswitch/trunk/libs/pcre/pcre_printint.src freeswitch/trunk/libs/pcre/pcre_refcount.c freeswitch/trunk/libs/pcre/pcre_scanner.cc freeswitch/trunk/libs/pcre/pcre_scanner.h freeswitch/trunk/libs/pcre/pcre_scanner_unittest.cc freeswitch/trunk/libs/pcre/pcre_stringpiece.cc freeswitch/trunk/libs/pcre/pcre_stringpiece.h.in freeswitch/trunk/libs/pcre/pcre_stringpiece_unittest.cc freeswitch/trunk/libs/pcre/pcre_study.c freeswitch/trunk/libs/pcre/pcre_tables.c freeswitch/trunk/libs/pcre/pcre_try_flipped.c freeswitch/trunk/libs/pcre/pcre_valid_utf8.c freeswitch/trunk/libs/pcre/pcre_version.c freeswitch/trunk/libs/pcre/pcre_xclass.c freeswitch/trunk/libs/pcre/pcrecpp.cc freeswitch/trunk/libs/pcre/pcrecpp.h freeswitch/trunk/libs/pcre/pcrecpp_unittest.cc freeswitch/trunk/libs/pcre/pcrecpparg.h.in freeswitch/trunk/libs/pcre/pcredemo.c freeswitch/trunk/libs/pcre/pcregrep.c freeswitch/trunk/libs/pcre/pcreposix.c freeswitch/trunk/libs/pcre/pcreposix.h freeswitch/trunk/libs/pcre/pcretest.c freeswitch/trunk/libs/pcre/testdata/grepinputx freeswitch/trunk/libs/pcre/testdata/grepoutput freeswitch/trunk/libs/pcre/testdata/testinput1 freeswitch/trunk/libs/pcre/testdata/testinput2 freeswitch/trunk/libs/pcre/testdata/testinput3 freeswitch/trunk/libs/pcre/testdata/testinput4 freeswitch/trunk/libs/pcre/testdata/testinput5 freeswitch/trunk/libs/pcre/testdata/testinput6 freeswitch/trunk/libs/pcre/testdata/testinput7 freeswitch/trunk/libs/pcre/testdata/testinput8 freeswitch/trunk/libs/pcre/testdata/testinput9 freeswitch/trunk/libs/pcre/testdata/testoutput1 freeswitch/trunk/libs/pcre/testdata/testoutput2 freeswitch/trunk/libs/pcre/testdata/testoutput3 freeswitch/trunk/libs/pcre/testdata/testoutput4 freeswitch/trunk/libs/pcre/testdata/testoutput5 freeswitch/trunk/libs/pcre/testdata/testoutput6 freeswitch/trunk/libs/pcre/testdata/testoutput7 freeswitch/trunk/libs/pcre/testdata/testoutput8 freeswitch/trunk/libs/pcre/testdata/testoutput9 freeswitch/trunk/libs/pcre/ucp.h Added: freeswitch/trunk/libs/pcre/132html ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/132html Mon Jun 8 18:51:30 2009 @@ -0,0 +1,296 @@ +#! /usr/bin/perl -w + +# Script to turn PCRE man pages into HTML + + +# Subroutine to handle font changes and other escapes + +sub do_line { +my($s) = $_[0]; + +$s =~ s/</</g; # Deal with < and > +$s =~ s/>/>/g; +$s =~ s"\\fI(.*?)\\f[RP]"<i>$1</i>"g; +$s =~ s"\\fB(.*?)\\f[RP]"<b>$1</b>"g; +$s =~ s"\\e"\\"g; +$s =~ s/(?<=Copyright )\(c\)/©/g; +$s; +} + +# Subroutine to ensure not in a paragraph + +sub end_para { +if ($inpara) + { + print TEMP "</PRE>\n" if ($inpre); + print TEMP "</P>\n"; + } +$inpara = $inpre = 0; +$wrotetext = 0; +} + +# Subroutine to start a new paragraph + +sub new_para { +&end_para(); +print TEMP "<P>\n"; +$inpara = 1; +} + + +# Main program + +$innf = 0; +$inpara = 0; +$inpre = 0; +$wrotetext = 0; +$toc = 0; +$ref = 1; + +while ($#ARGV >= 0 && $ARGV[0] =~ /^-/) + { + $toc = 1 if $ARGV[0] eq "-toc"; + shift; + } + +# Initial output to STDOUT + +print <<End ; +<html> +<head> +<title>$ARGV[0] specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>$ARGV[0] man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +End + +print "<ul>\n" if ($toc); + +open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n"; + +while (<STDIN>) + { + # Handle lines beginning with a dot + + if (/^\./) + { + # Some of the PCRE man pages used to contain instances of .br. However, + # they should have all been removed because they cause trouble in some + # (other) automated systems that translate man pages to HTML. Complain if + # we find .br or .in (another macro that is deprecated). + + if (/^\.br/ || /^\.in/) + { + print STDERR "\n*** Deprecated macro encountered - rewrite needed\n"; + print STDERR "*** $_\n"; + die "*** Processing abandoned\n"; + } + + # Instead of .br, relevent "literal" sections are enclosed in .nf/.fi. + + elsif (/^\.nf/) + { + $innf = 1; + } + + elsif (/^\.fi/) + { + $innf = 0; + } + + # Handling .sp is subtle. If it is inside a literal section, do nothing if + # the next line is a non literal text line; similarly, if not inside a + # literal section, do nothing if a literal follows. The point being that + # the <pre> and </pre> that delimit literal sections will do the spacing. + # Always skip if no previous output. + + elsif (/^\.sp/) + { + if ($wrotetext) + { + $_ = <STDIN>; + if ($inpre) + { + print TEMP "\n" if (/^[\s.]/); + } + else + { + print TEMP "<br>\n<br>\n" if (!/^[\s.]/); + } + redo; # Now process the lookahead line we just read + } + } + elsif (/^\.TP/ || /^\.PP/ || /^\.P/) + { + &new_para(); + } + elsif (/^\.SH\s*("?)(.*)\1/) + { + # Ignore the NAME section + if ($2 =~ /^NAME\b/) + { + <STDIN>; + next; + } + + &end_para(); + my($title) = &do_line($2); + if ($toc) + { + printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n", + $ref, $ref); + printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n", + $ref, $ref); + $ref++; + } + else + { + print TEMP "<br><b>\n$title\n</b><br>\n"; + } + } + elsif (/^\.SS\s*("?)(.*)\1/) + { + &end_para(); + my($title) = &do_line($2); + print TEMP "<br><b>\n$title\n</b><br>\n"; + } + elsif (/^\.B\s*(.*)/) + { + &new_para() if (!$inpara); + $_ = &do_line($1); + s/"(.*?)"/$1/g; + print TEMP "<b>$_</b>\n"; + $wrotetext = 1; + } + elsif (/^\.I\s*(.*)/) + { + &new_para() if (!$inpara); + $_ = &do_line($1); + s/"(.*?)"/$1/g; + print TEMP "<i>$_</i>\n"; + $wrotetext = 1; + } + + # A comment that starts "HREF" takes the next line as a name that + # is turned into a hyperlink, using the text given, which might be + # in a special font. If it ends in () or (digits) or punctuation, they + # aren't part of the link. + + elsif (/^\.\\"\s*HREF/) + { + $_=<STDIN>; + chomp; + $_ = &do_line($_); + $_ =~ s/\s+$//; + $_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/; + print TEMP "<a href=\"$1.html\">$_</a>\n"; + } + + # A comment that starts "HTML" inserts literal HTML + + elsif (/^\.\\"\s*HTML\s*(.*)/) + { + print TEMP $1; + } + + # A comment that starts < inserts that HTML at the end of the + # *next* input line - so as not to get a newline between them. + + elsif (/^\.\\"\s*(<.*>)/) + { + my($markup) = $1; + $_=<STDIN>; + chomp; + $_ = &do_line($_); + $_ =~ s/\s+$//; + print TEMP "$_$markup\n"; + } + + # A comment that starts JOIN joins the next two lines together, with one + # space between them. Then that line is processed. This is used in some + # displays where two lines are needed for the "man" version. JOINSH works + # the same, except that it assumes this is a shell command, so removes + # continuation backslashes. + + elsif (/^\.\\"\s*JOIN(SH)?/) + { + my($one,$two); + $one = <STDIN>; + $two = <STDIN>; + $one =~ s/\s*\\e\s*$// if (defined($1)); + chomp($one); + $two =~ s/^\s+//; + $_ = "$one $two"; + redo; # Process the joined lines + } + + # Ignore anything not recognized + + next; + } + + # Line does not begin with a dot. Replace blank lines with new paragraphs + + if (/^\s*$/) + { + &end_para() if ($wrotetext); + next; + } + + # Convert fonts changes and output an ordinary line. Ensure that indented + # lines are marked as literal. + + $_ = &do_line($_); + &new_para() if (!$inpara); + + if (/^\s/) + { + if (!$inpre) + { + print TEMP "<pre>\n"; + $inpre = 1; + } + } + elsif ($inpre) + { + print TEMP "</pre>\n"; + $inpre = 0; + } + + # Add <br> to the end of a non-literal line if we are within .nf/.fi + + $_ .= "<br>\n" if (!$inpre && $innf); + + print TEMP; + $wrotetext = 1; + } + +# The TOC, if present, will have been written - terminate it + +print "</ul>\n" if ($toc); + +# Copy the remainder to the standard output + +close(TEMP); +open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n"; + +print while (<TEMP>); + +print <<End ; +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +End + +close(TEMP); +unlink("/tmp/$$"); + +# End Modified: freeswitch/trunk/libs/pcre/AUTHORS ============================================================================== --- freeswitch/trunk/libs/pcre/AUTHORS (original) +++ freeswitch/trunk/libs/pcre/AUTHORS Mon Jun 8 18:51:30 2009 @@ -6,9 +6,9 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. +Cambridge, England. -Copyright (c) 1997-2006 University of Cambridge +Copyright (c) 1997-2009 University of Cambridge All rights reserved @@ -17,7 +17,7 @@ Written by: Google Inc. -Copyright (c) 2006 Google Inc +Copyright (c) 2007-2008 Google Inc All rights reserved #### Modified: freeswitch/trunk/libs/pcre/CMakeLists.txt ============================================================================== --- freeswitch/trunk/libs/pcre/CMakeLists.txt (original) +++ freeswitch/trunk/libs/pcre/CMakeLists.txt Mon Jun 8 18:51:30 2009 @@ -1,17 +1,578 @@ -cmake_minimum_required(VERSION 2.6) - -INCLUDE_DIRECTORIES(${CMAKE_SOURCE_DIR}/libs/pcre/include/ ${CMAKE_SOURCE_DIR}/libs/pcre/) - -SET ( pcre_SRCS pcre_compile.c pcre_tables.c pcre_config.c pcre_try_flipped.c pcre_dfa_exec.c pcre_ucp_searchfuncs.c pcre_exec.c pcre_valid_utf8.c pcre_fullinfo.c pcre_version.c dftables.c pcre_get.c pcre_xclass.c pcre_globals.c pcre_info.c pcrecpp.h pcre_internal.h pcre_maketables.c pcrecpparg.h pcre_ord2utf8.c pcredemo.c pcre_refcount.c pcregrep.c pcreposix.c pcre_scanner.h pcreposix.h pcre_scanner_unittest.cc pcretest.c pcre_stringpiece.h pcre_stringpiece.h.in ucp.h pcre.h ucpinternal.h pcre_chartables.c pcre.h ) - - - - -ADD_LIBRARY(pcre STATIC ${pcre_SRCS}) - - - - - - +# CMakeLists.txt +# +# +# This file allows building PCRE with the CMake configuration and build +# tool. Download CMake in source or binary form from http://www.cmake.org/ +# +# Original listfile by Christian Ehrlicher <Ch.Ehrlicher@gmx.de> +# Refined and expanded by Daniel Richard G. <skunk@iSKUNK.ORG> +# 2007-09-14 mod by Sheri so 7.4 supported configuration options can be entered +# 2007-09-19 Adjusted by PH to retain previous default settings +# 2007-12-26 (a) On UNIX, use names libpcre instead of just pcre +# (b) Ensure pcretest and pcregrep link with the local library, +# not a previously-installed one. +# (c) Add PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, and +# PCRE_SUPPORT_LIBBZ2. +# 2008-01-20 Brought up to date to include several new features by Christian +# Ehrlicher. +# 2008-01-22 Sheri added options for backward compatibility of library names +# when building with minGW: +# if "ON", NON_STANDARD_LIB_PREFIX causes shared libraries to +# be built without "lib" as prefix. (The libraries will be named +# pcre.dll, pcreposix.dll and pcrecpp.dll). +# if "ON", NON_STANDARD_LIB_SUFFIX causes shared libraries to +# be built with suffix of "-0.dll". (The libraries will be named +# libpcre-0.dll, libpcreposix-0.dll and libpcrecpp-0.dll - same names +# built by default with Configure and Make. +# 2008-01-23 PH removed the automatic build of pcredemo. +# 2008-04-22 PH modified READLINE support so it finds NCURSES when needed. +# 2008-07-03 PH updated for revised UCP property support (change of files) +# 2009-03-23 PH applied Steven Van Ingelgem's patch to change the name +# CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE +# is included within another project. +# 2009-03-23 PH applied a modified version of Steven Van Ingelgem's patches to +# add options to stop the building of pcregrep and the tests, and +# to disable the final configuration report. +# 2009-04-11 PH applied Christian Ehrlicher's patch to show compiler flags that +# are set by specifying a release type. + +PROJECT(PCRE C CXX) + +CMAKE_MINIMUM_REQUIRED(VERSION 2.4.6) + +SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake) # for FindReadline.cmake + +# external packages +FIND_PACKAGE( BZip2 ) +FIND_PACKAGE( ZLIB ) +FIND_PACKAGE( Readline ) + +# Configuration checks + +INCLUDE(CheckIncludeFile) +INCLUDE(CheckIncludeFileCXX) +INCLUDE(CheckFunctionExists) +INCLUDE(CheckTypeSize) + +CHECK_INCLUDE_FILE(dirent.h HAVE_DIRENT_H) +CHECK_INCLUDE_FILE(sys/stat.h HAVE_SYS_STAT_H) +CHECK_INCLUDE_FILE(sys/types.h HAVE_SYS_TYPES_H) +CHECK_INCLUDE_FILE(unistd.h HAVE_UNISTD_H) +CHECK_INCLUDE_FILE(windows.h HAVE_WINDOWS_H) + +CHECK_INCLUDE_FILE_CXX(type_traits.h HAVE_TYPE_TRAITS_H) +CHECK_INCLUDE_FILE_CXX(bits/type_traits.h HAVE_BITS_TYPE_TRAITS_H) + +CHECK_FUNCTION_EXISTS(bcopy HAVE_BCOPY) +CHECK_FUNCTION_EXISTS(memmove HAVE_MEMMOVE) +CHECK_FUNCTION_EXISTS(strerror HAVE_STRERROR) +CHECK_FUNCTION_EXISTS(strtoll HAVE_STRTOLL) +CHECK_FUNCTION_EXISTS(strtoq HAVE_STRTOQ) +CHECK_FUNCTION_EXISTS(_strtoi64 HAVE__STRTOI64) + +CHECK_TYPE_SIZE("long long" LONG_LONG) +CHECK_TYPE_SIZE("unsigned long long" UNSIGNED_LONG_LONG) + +# User-configurable options +# +# (Note: CMakeSetup displays these in alphabetical order, regardless of +# the order we use here) + +SET(BUILD_SHARED_LIBS OFF CACHE BOOL + "Build shared libraries instead of static ones.") + +OPTION(PCRE_BUILD_PCRECPP "Build the PCRE C++ library (pcrecpp)." ON) + +SET(PCRE_EBCDIC OFF CACHE BOOL + "Use EBCDIC coding instead of ASCII. (This is rarely used outside of mainframe systems)") + +SET(PCRE_LINK_SIZE "2" CACHE STRING + "Internal link size (2, 3 or 4 allowed). See LINK_SIZE in config.h.in for details.") + +SET(PCRE_MATCH_LIMIT "10000000" CACHE STRING + "Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.") + +SET(PCRE_MATCH_LIMIT_RECURSION "MATCH_LIMIT" CACHE STRING + "Default limit on internal recursion. See MATCH_LIMIT_RECURSION in config.h.in for details.") + +SET(PCRE_NEWLINE "LF" CACHE STRING + "What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF).") + +SET(PCRE_NO_RECURSE OFF CACHE BOOL + "If ON, then don't use stack recursion when matching. See NO_RECURSE in config.h.in for details.") + +SET(PCRE_POSIX_MALLOC_THRESHOLD "10" CACHE STRING + "Threshold for malloc() usage. See POSIX_MALLOC_THRESHOLD in config.h.in for details.") + +SET(PCRE_SUPPORT_UNICODE_PROPERTIES OFF CACHE BOOL + "Enable support for Unicode properties. (If set, UTF-8 support will be enabled as well)") + +SET(PCRE_SUPPORT_UTF8 OFF CACHE BOOL + "Enable support for the Unicode UTF-8 encoding.") + +SET(PCRE_SUPPORT_BSR_ANYCRLF OFF CACHE BOOL + "ON=Backslash-R matches only LF CR and CRLF, OFF=Backslash-R matches all Unicode Linebreaks") + +OPTION(PCRE_SHOW_REPORT "Show the final configuration report" ON) +OPTION(PCRE_BUILD_PCREGREP "Build pcregrep" ON) +OPTION(PCRE_BUILD_TESTS "Build the tests" ON) + +IF (PCRE_BUILD_TESTS) + IF (NOT PCRE_BUILD_PCREGREP) + MESSAGE(STATUS "** Building tests requires pcregrep: PCRE_BUILD_PCREGREP forced ON") + SET(PCRE_BUILD_PCREGREP ON) + ENDIF(NOT PCRE_BUILD_PCREGREP) +ENDIF(PCRE_BUILD_TESTS) + +IF (MINGW) + OPTION(NON_STANDARD_LIB_PREFIX + "ON=Shared libraries built in mingw will be named pcre.dll, etc., instead of libpcre.dll, etc." + OFF) + + OPTION(NON_STANDARD_LIB_SUFFIX + "ON=Shared libraries built in mingw will be named libpcre-0.dll, etc., instead of libpcre.dll, etc." + OFF) +ENDIF(MINGW) + +# bzip2 lib +IF(BZIP2_FOUND) + OPTION (PCRE_SUPPORT_LIBBZ2 "Enable support for linking pcregrep with libbz2." ON) +ENDIF(BZIP2_FOUND) +IF(PCRE_SUPPORT_LIBBZ2) + INCLUDE_DIRECTORIES(${BZIP2_INCLUDE_DIR}) +ENDIF(PCRE_SUPPORT_LIBBZ2) + +# zlib +IF(ZLIB_FOUND) + OPTION (PCRE_SUPPORT_LIBZ "Enable support for linking pcregrep with libz." ON) +ENDIF(ZLIB_FOUND) +IF(PCRE_SUPPORT_LIBZ) + INCLUDE_DIRECTORIES(${ZLIB_INCLUDE_DIR}) +ENDIF(PCRE_SUPPORT_LIBZ) + +# readline lib +IF(READLINE_FOUND) + OPTION (PCRE_SUPPORT_LIBREADLINE "Enable support for linking pcretest with libreadline." ON) +ENDIF(READLINE_FOUND) +IF(PCRE_SUPPORT_LIBREADLINE) + INCLUDE_DIRECTORIES(${READLINE_INCLUDE_DIR}) +ENDIF(PCRE_SUPPORT_LIBREADLINE) + +# Prepare build configuration + +SET(pcre_have_type_traits 0) +SET(pcre_have_bits_type_traits 0) + +IF(HAVE_TYPE_TRAITS_H) + SET(pcre_have_type_traits 1) +ENDIF(HAVE_TYPE_TRAITS_H) + +IF(HAVE_BITS_TYPE_TRAITS_H) + SET(pcre_have_bits_type_traits 1) +ENDIF(HAVE_BITS_TYPE_TRAITS_H) + +SET(pcre_have_long_long 0) +SET(pcre_have_ulong_long 0) + +IF(HAVE_LONG_LONG) + SET(pcre_have_long_long 1) +ENDIF(HAVE_LONG_LONG) + +IF(HAVE_UNSIGNED_LONG_LONG) + SET(pcre_have_ulong_long 1) +ENDIF(HAVE_UNSIGNED_LONG_LONG) + +IF(NOT BUILD_SHARED_LIBS) + SET(PCRE_STATIC 1) +ENDIF(NOT BUILD_SHARED_LIBS) + +IF(PCRE_SUPPORT_BSR_ANYCRLF) + SET(BSR_ANYCRLF 1) +ENDIF(PCRE_SUPPORT_BSR_ANYCRLF) + +IF(PCRE_SUPPORT_UTF8 OR PCRE_SUPPORT_UNICODE_PROPERTIES) + SET(SUPPORT_UTF8 1) +ENDIF(PCRE_SUPPORT_UTF8 OR PCRE_SUPPORT_UNICODE_PROPERTIES) + +IF(PCRE_SUPPORT_UNICODE_PROPERTIES) + SET(SUPPORT_UCP 1) +ENDIF(PCRE_SUPPORT_UNICODE_PROPERTIES) + +# This next one used to contain +# SET(PCRETEST_LIBS ${READLINE_LIBRARY}) +# but I was advised to add the NCURSES test as well, along with +# some modifications to cmake/FindReadline.cmake which should +# make it possible to override the default if necessary. PH + +IF(PCRE_SUPPORT_LIBREADLINE) + SET(SUPPORT_LIBREADLINE 1) + SET(PCRETEST_LIBS ${READLINE_LIBRARY} ${NCURSES_LIBRARY}) +ENDIF(PCRE_SUPPORT_LIBREADLINE) + +IF(PCRE_SUPPORT_LIBZ) + SET(SUPPORT_LIBZ 1) + SET(PCREGREP_LIBS ${PCREGREP_LIBS} ${ZLIB_LIBRARIES}) +ENDIF(PCRE_SUPPORT_LIBZ) + +IF(PCRE_SUPPORT_LIBBZ2) + SET(SUPPORT_LIBBZ2 1) + SET(PCREGREP_LIBS ${PCREGREP_LIBS} ${BZIP2_LIBRARIES}) +ENDIF(PCRE_SUPPORT_LIBBZ2) + +SET(NEWLINE "") + +IF(PCRE_NEWLINE STREQUAL "LF") + SET(NEWLINE "10") +ENDIF(PCRE_NEWLINE STREQUAL "LF") +IF(PCRE_NEWLINE STREQUAL "CR") + SET(NEWLINE "13") +ENDIF(PCRE_NEWLINE STREQUAL "CR") +IF(PCRE_NEWLINE STREQUAL "CRLF") + SET(NEWLINE "3338") +ENDIF(PCRE_NEWLINE STREQUAL "CRLF") +IF(PCRE_NEWLINE STREQUAL "ANY") + SET(NEWLINE "-1") +ENDIF(PCRE_NEWLINE STREQUAL "ANY") +IF(PCRE_NEWLINE STREQUAL "ANYCRLF") + SET(NEWLINE "-2") +ENDIF(PCRE_NEWLINE STREQUAL "ANYCRLF") + +IF(NEWLINE STREQUAL "") + MESSAGE(FATAL_ERROR "The PCRE_NEWLINE variable must be set to one of the following values: \"LF\", \"CR\", \"CRLF\", \"ANY\", \"ANYCRLF\".") +ENDIF(NEWLINE STREQUAL "") + +IF(PCRE_EBCDIC) + SET(EBCDIC 1) +ENDIF(PCRE_EBCDIC) + +IF(PCRE_NO_RECURSE) + SET(NO_RECURSE 1) +ENDIF(PCRE_NO_RECURSE) + +# Output files +CONFIGURE_FILE(config-cmake.h.in + ${PROJECT_BINARY_DIR}/config.h + @ONLY) + +CONFIGURE_FILE(pcre.h.generic + ${PROJECT_BINARY_DIR}/pcre.h + COPYONLY) + +# What about pcre-config and libpcre.pc? + +IF(PCRE_BUILD_PCRECPP) + CONFIGURE_FILE(pcre_stringpiece.h.in + ${PROJECT_BINARY_DIR}/pcre_stringpiece.h + @ONLY) + + CONFIGURE_FILE(pcrecpparg.h.in + ${PROJECT_BINARY_DIR}/pcrecpparg.h + @ONLY) +ENDIF(PCRE_BUILD_PCRECPP) + +# Character table generation + +OPTION(PCRE_REBUILD_CHARTABLES "Rebuild char tables" OFF) +IF(PCRE_REBUILD_CHARTABLES) + ADD_EXECUTABLE(dftables dftables.c) + + GET_TARGET_PROPERTY(DFTABLES_EXE dftables LOCATION) + + ADD_CUSTOM_COMMAND( + COMMENT "Generating character tables (pcre_chartables.c) for current locale" + DEPENDS dftables + COMMAND ${DFTABLES_EXE} + ARGS ${PROJECT_BINARY_DIR}/pcre_chartables.c + OUTPUT ${PROJECT_BINARY_DIR}/pcre_chartables.c + ) +ELSE(PCRE_REBUILD_CHARTABLES) + CONFIGURE_FILE(${PROJECT_SOURCE_DIR}/pcre_chartables.c.dist + ${PROJECT_BINARY_DIR}/pcre_chartables.c + COPYONLY) +ENDIF(PCRE_REBUILD_CHARTABLES) + +# Source code + +SET(PCRE_HEADERS ${PROJECT_BINARY_DIR}/pcre.h) + +SET(PCRE_SOURCES + ${PROJECT_BINARY_DIR}/pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_info.c + pcre_newline.c + pcre_maketables.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_study.c + pcre_tables.c + pcre_try_flipped.c + pcre_ucd.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c +) + +SET(PCREPOSIX_HEADERS pcreposix.h) + +SET(PCREPOSIX_SOURCES pcreposix.c) + +SET(PCRECPP_HEADERS + pcrecpp.h + pcre_scanner.h + ${PROJECT_BINARY_DIR}/pcrecpparg.h + ${PROJECT_BINARY_DIR}/pcre_stringpiece.h +) + +SET(PCRECPP_SOURCES + pcrecpp.cc + pcre_scanner.cc + pcre_stringpiece.cc +) + +# Build setup + +ADD_DEFINITIONS(-DHAVE_CONFIG_H) + +IF(MSVC) + ADD_DEFINITIONS(-D_CRT_SECURE_NO_DEPRECATE) +ENDIF(MSVC) + +SET(CMAKE_INCLUDE_CURRENT_DIR 1) +# needed to make sure to not link debug libs +# against release libs and vice versa +IF(WIN32) + SET(CMAKE_DEBUG_POSTFIX "d") +ENDIF(WIN32) + +SET(targets) + +# Libraries +# pcre +ADD_LIBRARY(pcre ${PCRE_HEADERS} ${PCRE_SOURCES} ${PROJECT_BINARY_DIR}/config.h) +SET(targets ${targets} pcre) +ADD_LIBRARY(pcreposix ${PCREPOSIX_HEADERS} ${PCREPOSIX_SOURCES}) +SET(targets ${targets} pcreposix) +TARGET_LINK_LIBRARIES(pcreposix pcre) +IF(MINGW AND NOT PCRE_STATIC) + IF(NON_STANDARD_LIB_PREFIX) + SET_TARGET_PROPERTIES(pcre pcreposix + PROPERTIES PREFIX "" + ) + ENDIF(NON_STANDARD_LIB_PREFIX) + + IF(NON_STANDARD_LIB_SUFFIX) + SET_TARGET_PROPERTIES(pcre pcreposix + PROPERTIES SUFFIX "-0.dll" + ) + ENDIF(NON_STANDARD_LIB_SUFFIX) +ENDIF(MINGW AND NOT PCRE_STATIC) + + +# pcrecpp +IF(PCRE_BUILD_PCRECPP) + ADD_LIBRARY(pcrecpp ${PCRECPP_HEADERS} ${PCRECPP_SOURCES}) +SET(targets ${targets} pcrecpp) + TARGET_LINK_LIBRARIES(pcrecpp pcre) + + IF(MINGW AND NOT PCRE_STATIC) + IF(NON_STANDARD_LIB_PREFIX) + SET_TARGET_PROPERTIES(pcrecpp + PROPERTIES PREFIX "" + ) + ENDIF(NON_STANDARD_LIB_PREFIX) + + IF(NON_STANDARD_LIB_SUFFIX) + SET_TARGET_PROPERTIES(pcrecpp + PROPERTIES SUFFIX "-0.dll" + ) + ENDIF(NON_STANDARD_LIB_SUFFIX) + ENDIF(MINGW AND NOT PCRE_STATIC) +ENDIF(PCRE_BUILD_PCRECPP) + + +# Executables + +# Removed by PH (2008-01-23) because pcredemo shouldn't really be built +# automatically, and it gave trouble in some environments anyway. +# ADD_EXECUTABLE(pcredemo pcredemo.c) +# TARGET_LINK_LIBRARIES(pcredemo pcreposix) +# IF(NOT BUILD_SHARED_LIBS) +# # make sure to not use declspec(dllimport) in static mode on windows +# SET_TARGET_PROPERTIES(pcredemo PROPERTIES COMPILE_FLAGS "-DPCRE_STATIC") +# ENDIF(NOT BUILD_SHARED_LIBS) + +IF(PCRE_BUILD_PCREGREP) + ADD_EXECUTABLE(pcregrep pcregrep.c) + SET(targets ${targets} pcregrep) + TARGET_LINK_LIBRARIES(pcregrep pcreposix ${PCREGREP_LIBS}) +ENDIF(PCRE_BUILD_PCREGREP) + + +# Testing +IF(PCRE_BUILD_TESTS) + ENABLE_TESTING() + + ADD_EXECUTABLE(pcretest pcretest.c) + SET(targets ${targets} pcretest) + TARGET_LINK_LIBRARIES(pcretest pcreposix ${PCRETEST_LIBS}) + + IF(PCRE_BUILD_PCRECPP) + ADD_EXECUTABLE(pcrecpp_unittest pcrecpp_unittest.cc) + SET(targets ${targets} pcrecpp_unittest) + TARGET_LINK_LIBRARIES(pcrecpp_unittest pcrecpp) + IF(MINGW AND NON_STANDARD_LIB_NAMES AND NOT PCRE_STATIC) + SET_TARGET_PROPERTIES(pcrecpp + PROPERTIES PREFIX "" + ) + ENDIF(MINGW AND NON_STANDARD_LIB_NAMES AND NOT PCRE_STATIC) + + + ADD_EXECUTABLE(pcre_scanner_unittest pcre_scanner_unittest.cc) + SET(targets ${targets} pcre_scanner_unittest) + TARGET_LINK_LIBRARIES(pcre_scanner_unittest pcrecpp) + + ADD_EXECUTABLE(pcre_stringpiece_unittest pcre_stringpiece_unittest.cc) + SET(targets ${targets} pcre_stringpiece_unittest) + TARGET_LINK_LIBRARIES(pcre_stringpiece_unittest pcrecpp) + ENDIF(PCRE_BUILD_PCRECPP) + + GET_TARGET_PROPERTY(PCREGREP_EXE pcregrep DEBUG_LOCATION) + GET_TARGET_PROPERTY(PCRETEST_EXE pcretest DEBUG_LOCATION) + + # Write out a CTest configuration file that sets some needed environment + # variables for the test scripts. + # + FILE(WRITE ${PROJECT_BINARY_DIR}/CTestCustom.ctest + "# This is a generated file. + SET(ENV{srcdir} ${PROJECT_SOURCE_DIR}) + SET(ENV{pcregrep} ${PCREGREP_EXE}) + SET(ENV{pcretest} ${PCRETEST_EXE}) + ") + + IF(UNIX) + ADD_TEST(pcre_test ${PROJECT_SOURCE_DIR}/RunTest) + ADD_TEST(pcre_grep_test ${PROJECT_SOURCE_DIR}/RunGrepTest) + ENDIF(UNIX) + IF(WIN32) + ADD_TEST(pcre_test cmd /C ${PROJECT_SOURCE_DIR}/RunTest.bat) + ENDIF(WIN32) + + GET_TARGET_PROPERTY(PCRECPP_UNITTEST_EXE + pcrecpp_unittest + DEBUG_LOCATION) + + GET_TARGET_PROPERTY(PCRE_SCANNER_UNITTEST_EXE + pcre_scanner_unittest + DEBUG_LOCATION) + + GET_TARGET_PROPERTY(PCRE_STRINGPIECE_UNITTEST_EXE + pcre_stringpiece_unittest + DEBUG_LOCATION) + + ADD_TEST(pcrecpp_test ${PCRECPP_UNITTEST_EXE}) + ADD_TEST(pcre_scanner_test ${PCRE_SCANNER_UNITTEST_EXE}) + ADD_TEST(pcre_stringpiece_test ${PCRE_STRINGPIECE_UNITTEST_EXE}) +ENDIF(PCRE_BUILD_TESTS) + +# Installation +SET(CMAKE_INSTALL_ALWAYS 1) + +INSTALL(TARGETS ${targets} + RUNTIME DESTINATION bin + LIBRARY DESTINATION lib + ARCHIVE DESTINATION lib) + +INSTALL(FILES ${PCRE_HEADERS} ${PCREPOSIX_HEADERS} DESTINATION include) + +FILE(GLOB html ${PROJECT_SOURCE_DIR}/doc/html/*.html) +FILE(GLOB man1 ${PROJECT_SOURCE_DIR}/doc/*.1) +FILE(GLOB man3 ${PROJECT_SOURCE_DIR}/doc/*.3) + +IF(PCRE_BUILD_PCRECPP) + INSTALL(FILES ${PCRECPP_HEADERS} DESTINATION include) +ELSE(PCRE_BUILD_PCRECPP) + # Remove pcrecpp.3 + FOREACH(man ${man3}) + GET_FILENAME_COMPONENT(man_tmp ${man} NAME) + IF(NOT man_tmp STREQUAL "pcrecpp.3") + SET(man3_new ${man3} ${man}) + ENDIF(NOT man_tmp STREQUAL "pcrecpp.3") + ENDFOREACH(man ${man3}) + SET(man3 ${man3_new}) +ENDIF(PCRE_BUILD_PCRECPP) + + +INSTALL(FILES ${man1} DESTINATION man/man1) +INSTALL(FILES ${man3} DESTINATION man/man3) +INSTALL(FILES ${html} DESTINATION share/doc/pcre/html) + +# help, only for nice output +IF(BUILD_SHARED_LIBS) + SET(BUILD_STATIC_LIBS OFF) +ELSE(BUILD_SHARED_LIBS) + SET(BUILD_STATIC_LIBS ON) +ENDIF(BUILD_SHARED_LIBS) + +IF(PCRE_SHOW_REPORT) + STRING(TOUPPER "${CMAKE_BUILD_TYPE}" buildtype) + IF (CMAKE_C_FLAGS) + SET(cfsp " ") + ENDIF(CMAKE_C_FLAGS) + IF (CMAKE_CXX_FLAGS) + SET(cxxfsp " ") + ENDIF(CMAKE_CXX_FLAGS) + MESSAGE(STATUS "") + MESSAGE(STATUS "") + MESSAGE(STATUS "PCRE configuration summary:") + MESSAGE(STATUS "") + MESSAGE(STATUS " Install prefix .................. : ${CMAKE_INSTALL_PREFIX}") + MESSAGE(STATUS " C compiler ...................... : ${CMAKE_C_COMPILER}") + MESSAGE(STATUS " C++ compiler .................... : ${CMAKE_CXX_COMPILER}") + MESSAGE(STATUS " C compiler flags ................ : ${CMAKE_C_FLAGS}${cfsp}${CMAKE_C_FLAGS_${buildtype}}") + MESSAGE(STATUS " C++ compiler flags .............. : ${CMAKE_CXX_FLAGS}${cxxfsp}${CMAKE_CXX_FLAGS_${buildtype}}") + MESSAGE(STATUS "") + MESSAGE(STATUS " Build C++ library ............... : ${PCRE_BUILD_PCRECPP}") + MESSAGE(STATUS " Enable UTF-8 support ............ : ${PCRE_SUPPORT_UNICODE_PROPERTIES}") + MESSAGE(STATUS " Unicode properties .............. : ${PCRE_SUPPORT_UNICODE_PROPERTIES}") + MESSAGE(STATUS " Newline char/sequence ........... : ${PCRE_NEWLINE}") + MESSAGE(STATUS " \\R matches only ANYCRLF ......... : ${PCRE_SUPPORT_BSR_ANYCRLF}") + MESSAGE(STATUS " EBCDIC coding ................... : ${PCRE_EBCDIC}") + MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE_REBUILD_CHARTABLES}") + MESSAGE(STATUS " No stack recursion .............. : ${PCRE_NO_RECURSE}") + MESSAGE(STATUS " POSIX mem threshold ............. : ${PCRE_POSIX_MALLOC_THRESHOLD}") + MESSAGE(STATUS " Internal link size .............. : ${PCRE_LINK_SIZE}") + MESSAGE(STATUS " Match limit ..................... : ${PCRE_MATCH_LIMIT}") + MESSAGE(STATUS " Match limit recursion ........... : ${PCRE_MATCH_LIMIT_RECURSION}") + MESSAGE(STATUS " Build shared libs ............... : ${BUILD_SHARED_LIBS}") + MESSAGE(STATUS " Build static libs ............... : ${BUILD_STATIC_LIBS}") + MESSAGE(STATUS " Build pcregrep .................. : ${PCRE_BUILD_PCREGREP}") + MESSAGE(STATUS " Build tests (implies pcretest) .. : ${PCRE_BUILD_TESTS}") + IF(ZLIB_FOUND) + MESSAGE(STATUS " Link pcregrep with libz ......... : ${PCRE_SUPPORT_LIBZ}") + ELSE(ZLIB_FOUND) + MESSAGE(STATUS " Link pcregrep with libz ......... : None" ) + ENDIF(ZLIB_FOUND) + IF(BZIP2_FOUND) + MESSAGE(STATUS " Link pcregrep with libbz2 ....... : ${PCRE_SUPPORT_LIBBZ2}") + ELSE(BZIP2_FOUND) + MESSAGE(STATUS " Link pcregrep with libbz2 ....... : None" ) + ENDIF(BZIP2_FOUND) + IF(NOT PCRE_SUPPORT_LIBREADLINE) + MESSAGE(STATUS " Link pcretest with libreadline .. : None" ) + ELSE(NOT PCRE_SUPPORT_LIBREADLINE) + MESSAGE(STATUS " Link pcretest with libreadline .. : ${PCRE_SUPPORT_LIBREADLINE}") + ENDIF(NOT PCRE_SUPPORT_LIBREADLINE) + IF(MINGW AND NOT PCRE_STATIC) + MESSAGE(STATUS " Non-standard dll names (prefix) . : ${NON_STANDARD_LIB_PREFIX}") + MESSAGE(STATUS " Non-standard dll names (suffix) . : ${NON_STANDARD_LIB_SUFFIX}") + ENDIF(MINGW AND NOT PCRE_STATIC) + MESSAGE(STATUS "") +ENDIF(PCRE_SHOW_REPORT) +# end CMakeLists.txt Modified: freeswitch/trunk/libs/pcre/COPYING ============================================================================== --- freeswitch/trunk/libs/pcre/COPYING (original) +++ freeswitch/trunk/libs/pcre/COPYING Mon Jun 8 18:51:30 2009 @@ -1,68 +1,5 @@ PCRE LICENCE ------------- -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Release 6 of PCRE is distributed under the terms of the "BSD" licence, as -specified below. The documentation for PCRE, supplied in the "doc" -directory, is distributed under the same terms as the software itself. - -The basic library functions are written in C and are freestanding. Also -included in the distribution is a set of C++ wrapper functions. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-2006 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2006, Google Inc. -All rights reserved. - - -THE "BSD" LICENCE ------------------ - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the name of Google - Inc. nor the names of their contributors may be used to endorse or - promote products derived from this software without specific prior - written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. +Please see the file LICENCE in the PCRE distribution for licensing details. End Modified: freeswitch/trunk/libs/pcre/ChangeLog ============================================================================== --- freeswitch/trunk/libs/pcre/ChangeLog (original) +++ freeswitch/trunk/libs/pcre/ChangeLog Mon Jun 8 18:51:30 2009 @@ -1,6 +1,1235 @@ ChangeLog for PCRE ------------------ +Version 7.9 11-Apr-09 +--------------------- + +1. When building with support for bzlib/zlib (pcregrep) and/or readline + (pcretest), all targets were linked against these libraries. This included + libpcre, libpcreposix, and libpcrecpp, even though they do not use these + libraries. This caused unwanted dependencies to be created. This problem + has been fixed, and now only pcregrep is linked with bzlib/zlib and only + pcretest is linked with readline. + +2. The "typedef int BOOL" in pcre_internal.h that was included inside the + "#ifndef FALSE" condition by an earlier change (probably 7.8/18) has been + moved outside it again, because FALSE and TRUE are already defined in AIX, + but BOOL is not. + +3. The pcre_config() function was treating the PCRE_MATCH_LIMIT and + PCRE_MATCH_LIMIT_RECURSION values as ints, when they should be long ints. + +4. The pcregrep documentation said spaces were inserted as well as colons (or + hyphens) following file names and line numbers when outputting matching + lines. This is not true; no spaces are inserted. I have also clarified the + wording for the --colour (or --color) option. + +5. In pcregrep, when --colour was used with -o, the list of matching strings + was not coloured; this is different to GNU grep, so I have changed it to be + the same. + +6. When --colo(u)r was used in pcregrep, only the first matching substring in + each matching line was coloured. Now it goes on to look for further matches + of any of the test patterns, which is the same behaviour as GNU grep. + +7. A pattern that could match an empty string could cause pcregrep to loop; it + doesn't make sense to accept an empty string match in pcregrep, so I have + locked it out (using PCRE's PCRE_NOTEMPTY option). By experiment, this + seems to be how GNU grep behaves. + +8. The pattern (?(?=.*b)b|^) was incorrectly compiled as "match must be at + start or after a newline", because the conditional assertion was not being + correctly handled. The rule now is that both the assertion and what follows + in the first alternative must satisfy the test. + +9. If auto-callout was enabled in a pattern with a conditional group whose + condition was an assertion, PCRE could crash during matching, both with + pcre_exec() and pcre_dfa_exec(). + +10. The PCRE_DOLLAR_ENDONLY option was not working when pcre_dfa_exec() was + used for matching. + +11. Unicode property support in character classes was not working for + characters (bytes) greater than 127 when not in UTF-8 mode. + +12. Added the -M command line option to pcretest. + +14. Added the non-standard REG_NOTEMPTY option to the POSIX interface. + +15. Added the PCRE_NO_START_OPTIMIZE match-time option. + +16. Added comments and documentation about mis-use of no_arg in the C++ + wrapper. + +17. Implemented support for UTF-8 encoding in EBCDIC environments, a patch + from Martin Jerabek that uses macro names for all relevant character and + string constants. + +18. Added to pcre_internal.h two configuration checks: (a) If both EBCDIC and + SUPPORT_UTF8 are set, give an error; (b) If SUPPORT_UCP is set without + SUPPORT_UTF8, define SUPPORT_UTF8. The "configure" script handles both of + these, but not everybody uses configure. + +19. A conditional group that had only one branch was not being correctly + recognized as an item that could match an empty string. This meant that an + enclosing group might also not be so recognized, causing infinite looping + (and probably a segfault) for patterns such as ^"((?(?=[a])[^"])|b)*"$ + with the subject "ab", where knowledge that the repeated group can match + nothing is needed in order to break the loop. + +20. If a pattern that was compiled with callouts was matched using pcre_dfa_ + exec(), but without supplying a callout function, matching went wrong. + +21. If PCRE_ERROR_MATCHLIMIT occurred during a recursion, there was a memory + leak if the size of the offset vector was greater than 30. When the vector + is smaller, the saved offsets during recursion go onto a local stack + vector, but for larger vectors malloc() is used. It was failing to free + when the recursion yielded PCRE_ERROR_MATCH_LIMIT (or any other "abnormal" + error, in fact). + +22. There was a missing #ifdef SUPPORT_UTF8 round one of the variables in the + heapframe that is used only when UTF-8 support is enabled. This caused no + problem, but was untidy. + +23. Steven Van Ingelgem's patch to CMakeLists.txt to change the name + CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE is + included within another project. + +24. Steven Van Ingelgem's patches to add more options to the CMake support, + slightly modified by me: + + (a) PCRE_BUILD_TESTS can be set OFF not to build the tests, including + not building pcregrep. + + (b) PCRE_BUILD_PCREGREP can be see OFF not to build pcregrep, but only + if PCRE_BUILD_TESTS is also set OFF, because the tests use pcregrep. + +25. Forward references, both numeric and by name, in patterns that made use of + duplicate group numbers, could behave incorrectly or give incorrect errors, + because when scanning forward to find the reference group, PCRE was not + taking into account the duplicate group numbers. A pattern such as + ^X(?3)(a)(?|(b)|(q))(Y) is an example. + +26. Changed a few more instances of "const unsigned char *" to USPTR, making + the feature of a custom pointer more persuasive (as requested by a user). + +27. Wrapped the definitions of fileno and isatty for Windows, which appear in + pcretest.c, inside #ifndefs, because it seems they are sometimes already + pre-defined. + +28. Added support for (*UTF8) at the start of a pattern. + +29. Arrange for flags added by the "release type" setting in CMake to be shown + in the configuration summary. + + +Version 7.8 05-Sep-08 +--------------------- + +1. Replaced UCP searching code with optimized version as implemented for Ad + Muncher (http://www.admuncher.com/) by Peter Kankowski. This uses a two- + stage table and inline lookup instead of a function, giving speed ups of 2 + to 5 times on some simple patterns that I tested. Permission was given to + distribute the MultiStage2.py script that generates the tables (it's not in + the tarball, but is in the Subversion repository). + +2. Updated the Unicode datatables to Unicode 5.1.0. This adds yet more + scripts. + +3. Change 12 for 7.7 introduced a bug in pcre_study() when a pattern contained + a group with a zero qualifier. The result of the study could be incorrect, + or the function might crash, depending on the pattern. + +4. Caseless matching was not working for non-ASCII characters in back + references. For example, /(\x{de})\1/8i was not matching \x{de}\x{fe}. + It now works when Unicode Property Support is available. + +5. In pcretest, an escape such as \x{de} in the data was always generating + a UTF-8 string, even in non-UTF-8 mode. Now it generates a single byte in + non-UTF-8 mode. If the value is greater than 255, it gives a warning about + truncation. + +6. Minor bugfix in pcrecpp.cc (change "" == ... to NULL == ...). + +7. Added two (int) casts to pcregrep when printing the difference of two + pointers, in case they are 64-bit values. + +8. Added comments about Mac OS X stack usage to the pcrestack man page and to + test 2 if it fails. + +9. Added PCRE_CALL_CONVENTION just before the names of all exported functions, + and a #define of that name to empty if it is not externally set. This is to + allow users of MSVC to set it if necessary. + +10. The PCRE_EXP_DEFN macro which precedes exported functions was missing from + the convenience functions in the pcre_get.c source file. + +11. An option change at the start of a pattern that had top-level alternatives + could cause overwriting and/or a crash. This command provoked a crash in + some environments: + + printf "/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8\n" | pcretest + + This potential security problem was recorded as CVE-2008-2371. + +12. For a pattern where the match had to start at the beginning or immediately + after a newline (e.g /.*anything/ without the DOTALL flag), pcre_exec() and + pcre_dfa_exec() could read past the end of the passed subject if there was + no match. To help with detecting such bugs (e.g. with valgrind), I modified + pcretest so that it places the subject at the end of its malloc-ed buffer. + +13. The change to pcretest in 12 above threw up a couple more cases when pcre_ + exec() might read past the end of the data buffer in UTF-8 mode. + +14. A similar bug to 7.3/2 existed when the PCRE_FIRSTLINE option was set and + the data contained the byte 0x85 as part of a UTF-8 character within its + first line. This applied both to normal and DFA matching. + +15. Lazy qualifiers were not working in some cases in UTF-8 mode. For example, + /^[^d]*?$/8 failed to match "abc". + +16. Added a missing copyright notice to pcrecpp_internal.h. + +17. Make it more clear in the documentation that values returned from + pcre_exec() in ovector are byte offsets, not character counts. + +18. Tidied a few places to stop certain compilers from issuing warnings. + +19. Updated the Virtual Pascal + BCC files to compile the latest v7.7, as + supplied by Stefan Weber. I made a further small update for 7.8 because + there is a change of source arrangements: the pcre_searchfuncs.c module is + replaced by pcre_ucd.c. + + +Version 7.7 07-May-08 +--------------------- + +1. Applied Craig's patch to sort out a long long problem: "If we can't convert + a string to a long long, pretend we don't even have a long long." This is + done by checking for the strtoq, strtoll, and _strtoi64 functions. + +2. Applied Craig's patch to pcrecpp.cc to restore ABI compatibility with + pre-7.6 versions, which defined a global no_arg variable instead of putting + it in the RE class. (See also #8 below.) + +3. Remove a line of dead code, identified by coverity and reported by Nuno + Lopes. + +4. Fixed two related pcregrep bugs involving -r with --include or --exclude: + + (1) The include/exclude patterns were being applied to the whole pathnames + of files, instead of just to the final components. + + (2) If there was more than one level of directory, the subdirectories were + skipped unless they satisfied the include/exclude conditions. This is + inconsistent with GNU grep (and could even be seen as contrary to the + pcregrep specification - which I improved to make it absolutely clear). + The action now is always to scan all levels of directory, and just + apply the include/exclude patterns to regular files. + +5. Added the --include_dir and --exclude_dir patterns to pcregrep, and used + --exclude_dir in the tests to avoid scanning .svn directories. + +6. Applied Craig's patch to the QuoteMeta function so that it escapes the + NUL character as backslash + 0 rather than backslash + NUL, because PCRE + doesn't support NULs in patterns. + +7. Added some missing "const"s to declarations of static tables in + pcre_compile.c and pcre_dfa_exec.c. + +8. Applied Craig's patch to pcrecpp.cc to fix a problem in OS X that was + caused by fix #2 above. (Subsequently also a second patch to fix the + first patch. And a third patch - this was a messy problem.) + +9. Applied Craig's patch to remove the use of push_back(). + +10. Applied Alan Lehotsky's patch to add REG_STARTEND support to the POSIX + matching function regexec(). + +11. Added support for the Oniguruma syntax \g<name>, \g<n>, \g'name', \g'n', + which, however, unlike Perl's \g{...}, are subroutine calls, not back + references. PCRE supports relative numbers with this syntax (I don't think + Oniguruma does). + +12. Previously, a group with a zero repeat such as (...){0} was completely + omitted from the compiled regex. However, this means that if the group + was called as a subroutine from elsewhere in the pattern, things went wrong + (an internal error was given). Such groups are now left in the compiled + pattern, with a new opcode that causes them to be skipped at execution + time. + +13. Added the PCRE_JAVASCRIPT_COMPAT option. This makes the following changes + to the way PCRE behaves: + + (a) A lone ] character is dis-allowed (Perl treats it as data). + + (b) A back reference to an unmatched subpattern matches an empty string + (Perl fails the current match path). + + (c) A data ] in a character class must be notated as \] because if the + first data character in a class is ], it defines an empty class. (In + Perl it is not possible to have an empty class.) The empty class [] + never matches; it forces failure and is equivalent to (*FAIL) or (?!). + The negative empty class [^] matches any one character, independently + of the DOTALL setting. + +14. A pattern such as /(?2)[]a()b](abc)/ which had a forward reference to a + non-existent subpattern following a character class starting with ']' and + containing () gave an internal compiling error instead of "reference to + non-existent subpattern". Fortunately, when the pattern did exist, the + compiled code was correct. (When scanning forwards to check for the + existencd of the subpattern, it was treating the data ']' as terminating + the class, so got the count wrong. When actually compiling, the reference + was subsequently set up correctly.) + +15. The "always fail" assertion (?!) is optimzed to (*FAIL) by pcre_compile; + it was being rejected as not supported by pcre_dfa_exec(), even though + other assertions are supported. I have made pcre_dfa_exec() support + (*FAIL). + +16. The implementation of 13c above involved the invention of a new opcode, + OP_ALLANY, which is like OP_ANY but doesn't check the /s flag. Since /s + cannot be changed at match time, I realized I could make a small + improvement to matching performance by compiling OP_ALLANY instead of + OP_ANY for "." when DOTALL was set, and then removing the runtime tests + on the OP_ANY path. + +17. Compiling pcretest on Windows with readline support failed without the + following two fixes: (1) Make the unistd.h include conditional on + HAVE_UNISTD_H; (2) #define isatty and fileno as _isatty and _fileno. + +18. Changed CMakeLists.txt and cmake/FindReadline.cmake to arrange for the + ncurses library to be included for pcretest when ReadLine support is + requested, but also to allow for it to be overridden. This patch came from + Daniel Bergstr�m. + +19. There was a typo in the file ucpinternal.h where f0_rangeflag was defined + as 0x00f00000 instead of 0x00800000. Luckily, this would not have caused + any errors with the current Unicode tables. Thanks to Peter Kankowski for + spotting this. + + +Version 7.6 28-Jan-08 +--------------------- + +1. A character class containing a very large number of characters with + codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer + overflow. + +2. Patch to cut out the "long long" test in pcrecpp_unittest when + HAVE_LONG_LONG is not defined. + +3. Applied Christian Ehrlicher's patch to update the CMake build files to + bring them up to date and include new features. This patch includes: + + - Fixed PH's badly added libz and libbz2 support. + - Fixed a problem with static linking. + - Added pcredemo. [But later removed - see 7 below.] + - Fixed dftables problem and added an option. + - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and + HAVE_LONG_LONG. + - Added readline support for pcretest. + - Added an listing of the option settings after cmake has run. + +4. A user submitted a patch to Makefile that makes it easy to create + "pcre.dll" under mingw when using Configure/Make. I added stuff to + Makefile.am that cause it to include this special target, without + affecting anything else. Note that the same mingw target plus all + the other distribution libraries and programs are now supported + when configuring with CMake (see 6 below) instead of with + Configure/Make. + +5. Applied Craig's patch that moves no_arg into the RE class in the C++ code. + This is an attempt to solve the reported problem "pcrecpp::no_arg is not + exported in the Windows port". It has not yet been confirmed that the patch + solves the problem, but it does no harm. + +6. Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and + NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured + with CMake, and also correct the comment about stack recursion. + +7. Remove the automatic building of pcredemo from the ./configure system and + from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example + of a program that users should build themselves after PCRE is installed, so + building it automatically is not really right. What is more, it gave + trouble in some build environments. + +8. Further tidies to CMakeLists.txt from Sheri and Christian. + + +Version 7.5 10-Jan-08 +--------------------- + +1. Applied a patch from Craig: "This patch makes it possible to 'ignore' + values in parens when parsing an RE using the C++ wrapper." + +2. Negative specials like \S did not work in character classes in UTF-8 mode. + Characters greater than 255 were excluded from the class instead of being + included. + +3. The same bug as (2) above applied to negated POSIX classes such as + [:^space:]. + +4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it + defined or documented. It seems to have been a typo for PCRE_STATIC, so + I have changed it. + +5. The construct (?&) was not diagnosed as a syntax error (it referenced the + first named subpattern) and a construct such as (?&a) would reference the + first named subpattern whose name started with "a" (in other words, the + length check was missing). Both these problems are fixed. "Subpattern name + expected" is now given for (?&) (a zero-length name), and this patch also + makes it give the same error for \k'' (previously it complained that that + was a reference to a non-existent subpattern). + +6. The erroneous patterns (?+-a) and (?-+a) give different error messages; + this is right because (?- can be followed by option settings as well as by + digits. I have, however, made the messages clearer. + +7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns + than the number used in the conditional) now cause a compile-time error. + This is actually not compatible with Perl, which accepts such patterns, but + treats the conditional as always being FALSE (as PCRE used to), but it + seems to me that giving a diagnostic is better. + +8. Change "alphameric" to the more common word "alphanumeric" in comments + and messages. + +9. Fix two occurrences of "backslash" in comments that should have been + "backspace". + +10. Remove two redundant lines of code that can never be obeyed (their function + was moved elsewhere). + +11. The program that makes PCRE's Unicode character property table had a bug + which caused it to generate incorrect table entries for sequences of + characters that have the same character type, but are in different scripts. + It amalgamated them into a single range, with the script of the first of + them. In other words, some characters were in the wrong script. There were + thirteen such cases, affecting characters in the following ranges: + + U+002b0 - U+002c1 + U+0060c - U+0060d + U+0061e - U+00612 + U+0064b - U+0065e + U+0074d - U+0076d + U+01800 - U+01805 + U+01d00 - U+01d77 + U+01d9b - U+01dbf + U+0200b - U+0200f + U+030fc - U+030fe + U+03260 - U+0327f + U+0fb46 - U+0fbb1 + U+10450 - U+1049d + +12. The -o option (show only the matching part of a line) for pcregrep was not + compatible with GNU grep in that, if there was more than one match in a + line, it showed only the first of them. It now behaves in the same way as + GNU grep. + +13. If the -o and -v options were combined for pcregrep, it printed a blank + line for every non-matching line. GNU grep prints nothing, and pcregrep now + does the same. The return code can be used to tell if there were any + non-matching lines. + +14. Added --file-offsets and --line-offsets to pcregrep. + +15. The pattern (?=something)(?R) was not being diagnosed as a potentially + infinitely looping recursion. The bug was that positive lookaheads were not + being skipped when checking for a possible empty match (negative lookaheads + and both kinds of lookbehind were skipped). + +16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the + inclusion of <windows.h> to before rather than after the definition of + INVALID_FILE_ATTRIBUTES (patch from David Byron). + +17. Specifying a possessive quantifier with a specific limit for a Unicode + character property caused pcre_compile() to compile bad code, which led at + runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this + are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that + caused the error; without that there was no problem. + +18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. + +19. Added --enable-pcretest-libreadline. + +20. In pcrecpp.cc, the variable 'count' was incremented twice in + RE::GlobalReplace(). As a result, the number of replacements returned was + double what it should be. I removed one of the increments, but Craig sent a + later patch that removed the other one (the right fix) and added unit tests + that check the return values (which was not done before). + +21. Several CMake things: + + (1) Arranged that, when cmake is used on Unix, the libraries end up with + the names libpcre and libpcreposix, not just pcre and pcreposix. + + (2) The above change means that pcretest and pcregrep are now correctly + linked with the newly-built libraries, not previously installed ones. + + (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. + +22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* + crashed when matching a string such as a\x{2029}b (note that \x{2029} is a + UTF-8 newline character). The key issue is that the pattern starts .*; + this means that the match must be either at the beginning, or after a + newline. The bug was in the code for advancing after a failed match and + checking that the new position followed a newline. It was not taking + account of UTF-8 characters correctly. + +23. PCRE was behaving differently from Perl in the way it recognized POSIX + character classes. PCRE was not treating the sequence [:...:] as a + character class unless the ... were all letters. Perl, however, seems to + allow any characters between [: and :], though of course it rejects as + unknown any "names" that contain non-letters, because all the known class + names consist only of letters. Thus, Perl gives an error for [[:1234:]], + for example, whereas PCRE did not - it did not recognize a POSIX character + class. This seemed a bit dangerous, so the code has been changed to be + closer to Perl. The behaviour is not identical to Perl, because PCRE will + diagnose an unknown class for, for example, [[:l\ower:]] where Perl will + treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where + Perl does, and where it didn't before. + +24. Rewrite so as to remove the single use of %n from pcregrep because in some + Windows environments %n is disabled by default. + + +Version 7.4 21-Sep-07 +--------------------- + +1. Change 7.3/28 was implemented for classes by looking at the bitmap. This + means that a class such as [\s] counted as "explicit reference to CR or + LF". That isn't really right - the whole point of the change was to try to + help when there was an actual mention of one of the two characters. So now + the change happens only if \r or \n (or a literal CR or LF) character is + encountered. + +2. The 32-bit options word was also used for 6 internal flags, but the numbers + of both had grown to the point where there were only 3 bits left. + Fortunately, there was spare space in the data structure, and so I have + moved the internal flags into a new 16-bit field to free up more option + bits. + +3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, + but did not set the internal JCHANGED flag - either of these is enough to + control the way the "get" function works - but the PCRE_INFO_JCHANGED + facility is supposed to tell if (?J) was ever used, so now (?J) at the + start sets both bits. + +4. Added options (at build time, compile time, exec time) to change \R from + matching any Unicode line ending sequence to just matching CR, LF, or CRLF. + +5. doc/pcresyntax.html was missing from the distribution. + +6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward + compatibility, even though it is no longer used. + +7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and + strtoull to pcrecpp.cc to select the available functions in WIN32 when the + windows.h file is present (where different names are used). [This was + reversed later after testing - see 16 below.] + +8. Changed all #include <config.h> to #include "config.h". There were also + some further <pcre.h> cases that I changed to "pcre.h". + +9. When pcregrep was used with the --colour option, it missed the line ending + sequence off the lines that it output. + +10. It was pointed out to me that arrays of string pointers cause lots of + relocations when a shared library is dynamically loaded. A technique of + using a single long string with a table of offsets can drastically reduce + these. I have refactored PCRE in four places to do this. The result is + dramatic: + + Originally: 290 + After changing UCP table: 187 + After changing error message table: 43 + After changing table of "verbs" 36 + After changing table of Posix names 22 + + Thanks to the folks working on Gregex for glib for this insight. + +11. --disable-stack-for-recursion caused compiling to fail unless -enable- + unicode-properties was also set. + +12. Updated the tests so that they work when \R is defaulted to ANYCRLF. + +13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously + checked only for CRLF. + +14. Added casts to pcretest.c to avoid compiler warnings. + +15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. + +16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, + and instead check for _strtoi64 explicitly, and avoid the use of snprintf() + entirely. This removes changes made in 7 above. + +17. The CMake files have been updated, and there is now more information about + building with CMake in the NON-UNIX-USE document. + + +Version 7.3 28-Aug-07 +--------------------- + + 1. In the rejigging of the build system that eventually resulted in 7.1, the + line "#include <pcre.h>" was included in pcre_internal.h. The use of angle + brackets there is not right, since it causes compilers to look for an + installed pcre.h, not the version that is in the source that is being + compiled (which of course may be different). I have changed it back to: + + #include "pcre.h" + + I have a vague recollection that the change was concerned with compiling in + different directories, but in the new build system, that is taken care of + by the VPATH setting the Makefile. + + 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed + when the subject happened to end in the byte 0x85 (e.g. if the last + character was \x{1ec5}). *Character* 0x85 is one of the "any" newline + characters but of course it shouldn't be taken as a newline when it is part + of another character. The bug was that, for an unlimited repeat of . in + not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by + characters when looking for a newline. + + 3. A small performance improvement in the DOTALL UTF-8 mode .* case. + + 4. Debugging: adjusted the names of opcodes for different kinds of parentheses + in debug output. + + 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for + long printing in the pcrecpp unittest when running under MinGW. + + 6. ESC_K was left out of the EBCDIC table. + + 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing + parentheses; I made it 1000, which seemed large enough. Unfortunately, the + limit also applies to "virtual nesting" when a pattern is recursive, and in + this case 1000 isn't so big. I have been able to remove this limit at the + expense of backing off one optimization in certain circumstances. Normally, + when pcre_exec() would call its internal match() function recursively and + immediately return the result unconditionally, it uses a "tail recursion" + feature to save stack. However, when a subpattern that can match an empty + string has an unlimited repetition quantifier, it no longer makes this + optimization. That gives it a stack frame in which to save the data for + checking that an empty string has been matched. Previously this was taken + from the 1000-entry workspace that had been reserved. So now there is no + explicit limit, but more stack is used. + + 8. Applied Daniel's patches to solve problems with the import/export magic + syntax that is required for Windows, and which was going wrong for the + pcreposix and pcrecpp parts of the library. These were overlooked when this + problem was solved for the main library. + + 9. There were some crude static tests to avoid integer overflow when computing + the size of patterns that contain repeated groups with explicit upper + limits. As the maximum quantifier is 65535, the maximum group length was + set at 30,000 so that the product of these two numbers did not overflow a + 32-bit integer. However, it turns out that people want to use groups that + are longer than 30,000 bytes (though not repeat them that many times). + Change 7.0/17 (the refactoring of the way the pattern size is computed) has + made it possible to implement the integer overflow checks in a much more + dynamic way, which I have now done. The artificial limitation on group + length has been removed - we now have only the limit on the total length of + the compiled pattern, which depends on the LINK_SIZE setting. + +10. Fixed a bug in the documentation for get/copy named substring when + duplicate names are permitted. If none of the named substrings are set, the + functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an + empty string. + +11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E + instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, + because the ] is interpreted as the first data character and the + terminating ] is not found. PCRE has been made compatible with Perl in this + regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could + cause memory overwriting. + +10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty + string has been matched (to stop an infinite loop). It was not recognizing + a conditional subpattern that could match an empty string if that + subpattern was within another subpattern. For example, it looped when + trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the + condition was not nested. This bug has been fixed. + +12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack + past the start of the subject in the presence of bytes with the top bit + set, for example "\x8aBCD". + +13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), + (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). + +14. Optimized (?!) to (*FAIL). + +15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. + This restricts code points to be within the range 0 to 0x10FFFF, excluding + the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the + full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still + does: it's just the validity check that is more restrictive. + +16. Inserted checks for integer overflows during escape sequence (backslash) + processing, and also fixed erroneous offset values for syntax errors during + backslash processing. + +17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) + for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". + +18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" + caused an overrun. + +19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with + something other than just ASCII characters) inside a group that had an + unlimited repeat caused a loop at compile time (while checking to see + whether the group could match an empty string). + +20. Debugging a pattern containing \p or \P could cause a crash. For example, + [\P{Any}] did so. (Error in the code for printing property names.) + +21. An orphan \E inside a character class could cause a crash. + +22. A repeated capturing bracket such as (A)? could cause a wild memory + reference during compilation. + +23. There are several functions in pcre_compile() that scan along a compiled + expression for various reasons (e.g. to see if it's fixed length for look + behind). There were bugs in these functions when a repeated \p or \P was + present in the pattern. These operators have additional parameters compared + with \d, etc, and these were not being taken into account when moving along + the compiled data. Specifically: + + (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed + length. + + (b) An item such as \pL+ within a repeated group could cause crashes or + loops. + + (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect + "reference to non-existent subpattern" error. + + (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. + +24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte + characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). + +25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. + +26. Patterns such as [\P{Yi}A] which include \p or \P and just one other + character were causing crashes (broken optimization). + +27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing + \p or \P) caused a compile-time loop. + +28. More problems have arisen in unanchored patterns when CRLF is a valid line + break. For example, the unstudied pattern [\r\n]A does not match the string + "\r\nA" because change 7.0/46 below moves the current point on by two + characters after failing to match at the start. However, the pattern \nA + *does* match, because it doesn't start till \n, and if [\r\n]A is studied, + the same is true. There doesn't seem any very clean way out of this, but + what I have chosen to do makes the common cases work: PCRE now takes note + of whether there can be an explicit match for \r or \n anywhere in the + pattern, and if so, 7.0/46 no longer applies. As part of this change, + there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled + pattern has explicit CR or LF references. + +29. Added (*CR) etc for changing newline setting at start of pattern. + + +Version 7.2 19-Jun-07 +--------------------- + + 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, + which is apparently normally available under Windows. + + 2. Re-jig the pcregrep tests with different newline settings in an attempt + to make them independent of the local environment's newline setting. + + 3. Add code to configure.ac to remove -g from the CFLAGS default settings. + + 4. Some of the "internals" tests were previously cut out when the link size + was not 2, because the output contained actual offsets. The recent new + "Z" feature of pcretest means that these can be cut out, making the tests + usable with all link sizes. + + 5. Implemented Stan Switzer's goto replacement for longjmp() when not using + stack recursion. This gives a massive performance boost under BSD, but just + a small improvement under Linux. However, it saves one field in the frame + in all cases. + + 6. Added more features from the forthcoming Perl 5.10: + + (a) (?-n) (where n is a string of digits) is a relative subroutine or + recursion call. It refers to the nth most recently opened parentheses. + + (b) (?+n) is also a relative subroutine call; it refers to the nth next + to be opened parentheses. + + (c) Conditions that refer to capturing parentheses can be specified + relatively, for example, (?(-2)... or (?(+3)... + + (d) \K resets the start of the current match so that everything before + is not part of it. + + (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible). + + (f) \g{name} is another synonym - part of Perl 5.10's unification of + reference syntax. + + (g) (?| introduces a group in which the numbering of parentheses in each + alternative starts with the same number. + + (h) \h, \H, \v, and \V match horizontal and vertical whitespace. + + 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and + PCRE_INFO_JCHANGED. + + 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not + terminating or by crashing. Diagnosed by Viktor Griph; it was in the code + for detecting groups that can match an empty string. + + 9. A pattern with a very large number of alternatives (more than several + hundred) was running out of internal workspace during the pre-compile + phase, where pcre_compile() figures out how much memory will be needed. A + bit of new cunning has reduced the workspace needed for groups with + alternatives. The 1000-alternative test pattern now uses 12 bytes of + workspace instead of running out of the 4096 that are available. + +10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. + +11. Applied patch from Google to remove an optimization that didn't quite work. + The report of the bug said: + + pcrecpp::RE("a*").FullMatch("aaa") matches, while + pcrecpp::RE("a*?").FullMatch("aaa") does not, and + pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. + +12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 + it matched the wrong number of bytes. + + +Version 7.1 24-Apr-07 +--------------------- + + 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one + that is more "standard", making use of automake and other Autotools. There + is some re-arrangement of the files and adjustment of comments consequent + on this. + + 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r + for recursive directory scanning broke on some systems because the files + are not scanned in any specific order and on different systems the order + was different. A call to "sort" has been inserted into RunGrepTest for the + approprate test as a short-term fix. In the longer term there may be an + alternative. + + 3. I had an email from Eric Raymond about problems translating some of PCRE's + man pages to HTML (despite the fact that I distribute HTML pages, some + people do their own conversions for various reasons). The problems + concerned the use of low-level troff macros .br and .in. I have therefore + removed all such uses from the man pages (some were redundant, some could + be replaced by .nf/.fi pairs). The 132html script that I use to generate + HTML has been updated to handle .nf/.fi and to complain if it encounters + .br or .in. + + 4. Updated comments in configure.ac that get placed in config.h.in and also + arranged for config.h to be included in the distribution, with the name + config.h.generic, for the benefit of those who have to compile without + Autotools (compare pcre.h, which is now distributed as pcre.h.generic). + + 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan + Weber: (1) pcre_internal.h was missing some function renames; (2) updated + makevp.bat for the current PCRE, using the additional files + makevp_c.txt, makevp_l.txt, and pcregexp.pas. + + 6. A Windows user reported a minor discrepancy with test 2, which turned out + to be caused by a trailing space on an input line that had got lost in his + copy. The trailing space was an accident, so I've just removed it. + + 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told + that is needed. + + 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) + as "const" (a) because they are and (b) because it helps the PHP + maintainers who have recently made a script to detect big data structures + in the php code that should be moved to the .rodata section. I remembered + to update Builducptable as well, so it won't revert if ucptable.h is ever + re-created. + + 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, + pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in + order to be able to cut out the UTF-8 tables in the latter when UTF-8 + support is not required. This saves 1.5-2K of code, which is important in + some applications. + + Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c + so as not to refer to the tables, even though these functions will never be + called when UTF-8 support is disabled. Otherwise there are problems with a + shared library. + +10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: + + (a) It was defining its arguments as char * instead of void *. + + (b) It was assuming that all moves were upwards in memory; this was true + a long time ago when I wrote it, but is no longer the case. + + The emulated memove() is provided for those environments that have neither + memmove() nor bcopy(). I didn't think anyone used it these days, but that + is clearly not the case, as these two bugs were recently reported. + +11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, + and Detrail to create the HTML documentation, the .txt form of the man + pages, and it removes trailing spaces from listed files. It also creates + pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter + case, it wraps all the #defines with #ifndefs. This script should be run + before "make dist". + +12. Fixed two fairly obscure bugs concerned with quantified caseless matching + with Unicode property support. + + (a) For a maximizing quantifier, if the two different cases of the + character were of different lengths in their UTF-8 codings (there are + some cases like this - I found 11), and the matching function had to + back up over a mixture of the two cases, it incorrectly assumed they + were both the same length. + + (b) When PCRE was configured to use the heap rather than the stack for + recursion during matching, it was not correctly preserving the data for + the other case of a UTF-8 character when checking ahead for a match + while processing a minimizing repeat. If the check also involved + matching a wide character, but failed, corruption could cause an + erroneous result when trying to check for a repeat of the original + character. + +13. Some tidying changes to the testing mechanism: + + (a) The RunTest script now detects the internal link size and whether there + is UTF-8 and UCP support by running ./pcretest -C instead of relying on + values substituted by "configure". (The RunGrepTest script already did + this for UTF-8.) The configure.ac script no longer substitutes the + relevant variables. + + (b) The debugging options /B and /D in pcretest show the compiled bytecode + with length and offset values. This means that the output is different + for different internal link sizes. Test 2 is skipped for link sizes + other than 2 because of this, bypassing the problem. Unfortunately, + there was also a test in test 3 (the locale tests) that used /B and + failed for link sizes other than 2. Rather than cut the whole test out, + I have added a new /Z option to pcretest that replaces the length and + offset values with spaces. This is now used to make test 3 independent + of link size. (Test 2 will be tidied up later.) + +14. If erroroffset was passed as NULL to pcre_compile, it provoked a + segmentation fault instead of returning the appropriate error message. + +15. In multiline mode when the newline sequence was set to "any", the pattern + ^$ would give a match between the \r and \n of a subject such as "A\r\nB". + This doesn't seem right; it now treats the CRLF combination as the line + ending, and so does not match in that case. It's only a pattern such as ^$ + that would hit this one: something like ^ABC$ would have failed after \r + and then tried again after \r\n. + +16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" + in an attempt to make files that differ only in their line terminators + compare equal. This works on Linux. + +17. Under certain error circumstances pcregrep might try to free random memory + as it exited. This is now fixed, thanks to valgrind. + +19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string + "abc\r\n\r\n", it found an unwanted second match after the second \r. This + was because its rules for how to advance for /g after matching an empty + string at the end of a line did not allow for this case. They now check for + it specially. + +20. pcretest is supposed to handle patterns and data of any length, by + extending its buffers when necessary. It was getting this wrong when the + buffer for a data line had to be extended. + +21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or + CRLF as a newline sequence. + +22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut + out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but + I have nevertheless tidied it up. + +23. Added some casts to kill warnings from HP-UX ia64 compiler. + +24. Added a man page for pcre-config. + + +Version 7.0 19-Dec-06 +--------------------- + + 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by + moving to gcc 4.1.1. + + 2. The -S option for pcretest uses setrlimit(); I had omitted to #include + sys/time.h, which is documented as needed for this function. It doesn't + seem to matter on Linux, but it showed up on some releases of OS X. + + 3. It seems that there are systems where bytes whose values are greater than + 127 match isprint() in the "C" locale. The "C" locale should be the + default when a C program starts up. In most systems, only ASCII printing + characters match isprint(). This difference caused the output from pcretest + to vary, making some of the tests fail. I have changed pcretest so that: + + (a) When it is outputting text in the compiled version of a pattern, bytes + other than 32-126 are always shown as hex escapes. + + (b) When it is outputting text that is a matched part of a subject string, + it does the same, unless a different locale has been set for the match + (using the /L modifier). In this case, it uses isprint() to decide. + + 4. Fixed a major bug that caused incorrect computation of the amount of memory + required for a compiled pattern when options that changed within the + pattern affected the logic of the preliminary scan that determines the + length. The relevant options are -x, and -i in UTF-8 mode. The result was + that the computed length was too small. The symptoms of this bug were + either the PCRE error "internal error: code overflow" from pcre_compile(), + or a glibc crash with a message such as "pcretest: free(): invalid next + size (fast)". Examples of patterns that provoked this bug (shown in + pcretest format) are: + + /(?-x: )/x + /(?x)(?-x: \s*#\s*)/ + /((?i)[\x{c0}])/8 + /(?i:[\x{c0}])/8 + + HOWEVER: Change 17 below makes this fix obsolete as the memory computation + is now done differently. + + 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ + wrapper classes; (b) implement a new function in the C++ scanner that is + more efficient than the old way of doing things because it avoids levels of + recursion in the regex matching; (c) add a paragraph to the documentation + for the FullMatch() function. + + 6. The escape sequence \n was being treated as whatever was defined as + "newline". Not only was this contrary to the documentation, which states + that \n is character 10 (hex 0A), but it also went horribly wrong when + "newline" was defined as CRLF. This has been fixed. + + 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) + was being set to -1 for the "end of line" case (supposedly a value that no + character can have). Though this value is never used (the check for end of + line is "zero bytes in current character"), it caused compiler complaints. + I've changed it to 0xffffffff. + + 8. In pcre_version.c, the version string was being built by a sequence of + C macros that, in the event of PCRE_PRERELEASE being defined as an empty + string (as it is for production releases) called a macro with an empty + argument. The C standard says the result of this is undefined. The gcc + compiler treats it as an empty string (which was what was wanted) but it is + reported that Visual C gives an error. The source has been hacked around to + avoid this problem. + + 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows + builds of pcretest, and changed the call to _setmode() to use _O_BINARY + instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all + of them did). + +10. Originally, pcretest opened its input and output without "b"; then I was + told that "b" was needed in some environments, so it was added for release + 5.0 to both the input and output. (It makes no difference on Unix-like + systems.) Later I was told that it is wrong for the input on Windows. I've + now abstracted the modes into two macros, to make it easier to fiddle with + them, and removed "b" from the input mode under Windows. + +11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. + +12. Added -help and --help to pcretest as an official way of being reminded + of the options. + +13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in + and pcrecpp.cc because they annoy compilers at high warning levels. + +14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. + +15. Fixed an occurrence of == in configure.ac that should have been = (shell + scripts are not C programs :-) and which was not noticed because it works + on Linux. + +16. pcretest is supposed to handle any length of pattern and data line (as one + line or as a continued sequence of lines) by extending its input buffer if + necessary. This feature was broken for very long pattern lines, leading to + a string of junk being passed to pcre_compile() if the pattern was longer + than about 50K. + +17. I have done a major re-factoring of the way pcre_compile() computes the + amount of memory needed for a compiled pattern. Previously, there was code + that made a preliminary scan of the pattern in order to do this. That was + OK when PCRE was new, but as the facilities have expanded, it has become + harder and harder to keep it in step with the real compile phase, and there + have been a number of bugs (see for example, 4 above). I have now found a + cunning way of running the real compile function in a "fake" mode that + enables it to compute how much memory it would need, while actually only + ever using a few hundred bytes of working memory and without too many + tests of the mode. This should make future maintenance and development + easier. A side effect of this work is that the limit of 200 on the nesting + depth of parentheses has been removed (though this was never a serious + limitation, I suspect). However, there is a downside: pcre_compile() now + runs more slowly than before (30% or more, depending on the pattern). I + hope this isn't a big issue. There is no effect on runtime performance. + +18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a + newline (only possible for the last line of a file) and it was a + pattern that set a locale (followed by /Lsomething), pcretest crashed. + +19. Added additional timing features to pcretest. (1) The -tm option now times + matching only, not compiling. (2) Both -t and -tm can be followed, as a + separate command line item, by a number that specifies the number of + repeats to use when timing. The default is 50000; this gives better + precision, but takes uncomfortably long for very large patterns. + +20. Extended pcre_study() to be more clever in cases where a branch of a + subpattern has no definite first character. For example, (a*|b*)[cd] would + previously give no result from pcre_study(). Now it recognizes that the + first character must be a, b, c, or d. + +21. There was an incorrect error "recursive call could loop indefinitely" if + a subpattern (or the entire pattern) that was being tested for matching an + empty string contained only one non-empty item after a nested subpattern. + For example, the pattern (?>\x{100}*)\d(?R) provoked this error + incorrectly, because the \d was being skipped in the check. + +22. The pcretest program now has a new pattern option /B and a command line + option -b, which is equivalent to adding /B to every pattern. This causes + it to show the compiled bytecode, without the additional information that + -d shows. The effect of -d is now the same as -b with -i (and similarly, /D + is the same as /B/I). + +23. A new optimization is now able automatically to treat some sequences such + as a*b as a*+b. More specifically, if something simple (such as a character + or a simple class like \d) has an unlimited quantifier, and is followed by + something that cannot possibly match the quantified thing, the quantifier + is automatically "possessified". + +24. A recursive reference to a subpattern whose number was greater than 39 + went wrong under certain circumstances in UTF-8 mode. This bug could also + have affected the operation of pcre_study(). + +25. Realized that a little bit of performance could be had by replacing + (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. + +26. Timing data from pcretest is now shown to 4 decimal places instead of 3. + +27. Possessive quantifiers such as a++ were previously implemented by turning + them into atomic groups such as ($>a+). Now they have their own opcodes, + which improves performance. This includes the automatically created ones + from 23 above. + +28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a + lookahead was broken if it was not anchored. PCRE was mistakenly expecting + the first matched character to be a colon. This applied both to named and + numbered groups. + +29. The ucpinternal.h header file was missing its idempotency #ifdef. + +30. I was sent a "project" file called libpcre.a.dev which I understand makes + building PCRE on Windows easier, so I have included it in the distribution. + +31. There is now a check in pcretest against a ridiculously large number being + returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G + loop, the loop is abandoned. + +32. Forward references to subpatterns in conditions such as (?(2)...) where + subpattern 2 is defined later cause pcre_compile() to search forwards in + the pattern for the relevant set of parentheses. This search went wrong + when there were unescaped parentheses in a character class, parentheses + escaped with \Q...\E, or parentheses in a #-comment in /x mode. + +33. "Subroutine" calls and backreferences were previously restricted to + referencing subpatterns earlier in the regex. This restriction has now + been removed. + +34. Added a number of extra features that are going to be in Perl 5.10. On the + whole, these are just syntactic alternatives for features that PCRE had + previously implemented using the Python syntax or my own invention. The + other formats are all retained for compatibility. + + (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well + as (?P<name>...). The new forms, as well as being in Perl 5.10, are + also .NET compatible. + + (b) A recursion or subroutine call to a named group can now be defined as + (?&name) as well as (?P>name). + + (c) A backreference to a named group can now be defined as \k<name> or + \k'name' as well as (?P=name). The new forms, as well as being in Perl + 5.10, are also .NET compatible. + + (d) A conditional reference to a named group can now use the syntax + (?(<name>) or (?('name') as well as (?(name). + + (e) A "conditional group" of the form (?(DEFINE)...) can be used to define + groups (named and numbered) that are never evaluated inline, but can be + called as "subroutines" from elsewhere. In effect, the DEFINE condition + is always false. There may be only one alternative in such a group. + + (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well + as the simple (?(R). The condition is true only if the most recent + recursion is that of the given number or name. It does not search out + through the entire recursion stack. + + (g) The escape \gN or \g{N} has been added, where N is a positive or + negative number, specifying an absolute or relative reference. + +35. Tidied to get rid of some further signed/unsigned compiler warnings and + some "unreachable code" warnings. + +36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other + things, this adds five new scripts. + +37. Perl ignores orphaned \E escapes completely. PCRE now does the same. + There were also incompatibilities regarding the handling of \Q..\E inside + character classes, for example with patterns like [\Qa\E-\Qz\E] where the + hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. + +38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group + matches an empty string, and forcibly breaks the loop. There were bugs in + this code in non-simple cases. For a pattern such as ^(a()*)* matched + against aaaa the result was just "a" rather than "aaaa", for example. Two + separate and independent bugs (that affected different cases) have been + fixed. + +39. Refactored the code to abolish the use of different opcodes for small + capturing bracket numbers. This is a tidy that I avoided doing when I + removed the limit on the number of capturing brackets for 3.5 back in 2001. + The new approach is not only tidier, it makes it possible to reduce the + memory needed to fix the previous bug (38). + +40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline + sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when + processing dot, circumflex, or dollar metacharacters, or #-comments in /x + mode. + +41. Add \R to match any Unicode newline sequence, as suggested in the Unicode + report. + +42. Applied patch, originally from Ari Pollak, modified by Google, to allow + copy construction and assignment in the C++ wrapper. + +43. Updated pcregrep to support "--newline=any". In the process, I fixed a + couple of bugs that could have given wrong results in the "--newline=crlf" + case. + +44. Added a number of casts and did some reorganization of signed/unsigned int + variables following suggestions from Dair Grant. Also renamed the variable + "this" as "item" because it is a C++ keyword. + +45. Arranged for dftables to add + + #include "pcre_internal.h" + + to pcre_chartables.c because without it, gcc 4.x may remove the array + definition from the final binary if PCRE is built into a static library and + dead code stripping is activated. + +46. For an unanchored pattern, if a match attempt fails at the start of a + newline sequence, and the newline setting is CRLF or ANY, and the next two + characters are CRLF, advance by two characters instead of one. + + Version 6.7 04-Jul-06 --------------------- Added: freeswitch/trunk/libs/pcre/CleanTxt ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/CleanTxt Mon Jun 8 18:51:30 2009 @@ -0,0 +1,113 @@ +#! /usr/bin/perl -w + +# Script to take the output of nroff -man and remove all the backspacing and +# the page footers and the screen commands etc so that it is more usefully +# readable online. In fact, in the latest nroff, intermediate footers don't +# seem to be generated any more. + +$blankcount = 0; +$lastwascut = 0; +$firstheader = 1; + +# Input on STDIN; output to STDOUT. + +while (<STDIN>) + { + s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" + s/.\x8//g; # Remove "char, backspace" + + # Handle header lines. Retain only the first one we encounter, but remove + # the blank line that follows. Any others (e.g. at end of document) and the + # following blank line are dropped. + + if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/) + { + if ($firstheader) + { + $firstheader = 0; + print; + $lastprinted = $_; + $lastwascut = 0; + } + $_=<STDIN>; # Remove a blank that follows + next; + } + + # Count runs of empty lines + + if (/^\s*$/) + { + $blankcount++; + $lastwascut = 0; + next; + } + + # If a chunk of lines has been cut out (page footer) and the next line + # has a different indentation, put back one blank line. + + if ($lastwascut && $blankcount < 1 && defined($lastprinted)) + { + ($a) = $lastprinted =~ /^(\s*)/; + ($b) = $_ =~ /^(\s*)/; + $blankcount++ if ($a ne $b); + } + + # We get here only when we have a non-blank line in hand. If it was preceded + # by 3 or more blank lines, read the next 3 lines and see if they are blank. + # If so, remove all 7 lines, and remember that we have just done a cut. + + if ($blankcount >= 3) + { + for ($i = 0; $i < 3; $i++) + { + $next[$i] = <STDIN>; + $next[$i] = "" if !defined $next[$i]; + $next[$i] =~ s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" + $next[$i] =~ s/.\x8//g; # Remove "char, backspace" + } + + # Cut out chunks of the form <3 blanks><non-blank><3 blanks> + + if ($next[0] =~ /^\s*$/ && + $next[1] =~ /^\s*$/ && + $next[2] =~ /^\s*$/) + { + $blankcount -= 3; + $lastwascut = 1; + } + + # Otherwise output the saved blanks, the current, and the next three + # lines. Remember the last printed line. + + else + { + for ($i = 0; $i < $blankcount; $i++) { print "\n"; } + print; + for ($i = 0; $i < 3; $i++) + { + $next[$i] =~ s/.\x8//g; + print $next[$i]; + $lastprinted = $_; + } + $lastwascut = 0; + $blankcount = 0; + } + } + + # This non-blank line is not preceded by 3 or more blank lines. Output + # any blanks there are, and the line. Remember it. Force two blank lines + # before headings. + + else + { + $blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ && + defined($lastprinted); + for ($i = 0; $i < $blankcount; $i++) { print "\n"; } + print; + $lastprinted = $_; + $lastwascut = 0; + $blankcount = 0; + } + } + +# End Added: freeswitch/trunk/libs/pcre/Detrail ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/Detrail Mon Jun 8 18:51:30 2009 @@ -0,0 +1,35 @@ +#!/usr/bin/perl + +# This is a script for removing trailing whitespace from lines in files that +# are listed on the command line. + +# This subroutine does the work for one file. + +sub detrail { +my($file) = $_[0]; +my($changed) = 0; +open(IN, "$file") || die "Can't open $file for input"; +@lines = <IN>; +close(IN); +foreach (@lines) + { + if (/\s+\n$/) + { + s/\s+\n$/\n/; + $changed = 1; + } + } +if ($changed) + { + open(OUT, ">$file") || die "Can't open $file for output"; + print OUT @lines; + close(OUT); + } +} + +# This is the main program + +$, = ""; # Output field separator +for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); } + +# End Added: freeswitch/trunk/libs/pcre/HACKING ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/HACKING Mon Jun 8 18:51:30 2009 @@ -0,0 +1,418 @@ +Technical Notes about PCRE +-------------------------- + +These are very rough technical notes that record potentially useful information +about PCRE internals. + +Historical note 1 +----------------- + +Many years ago I implemented some regular expression functions to an algorithm +suggested by Martin Richards. These were not Unix-like in form, and were quite +restricted in what they could do by comparison with Perl. The interesting part +about the algorithm was that the amount of space required to hold the compiled +form of an expression was known in advance. The code to apply an expression did +not operate by backtracking, as the original Henry Spencer code and current +Perl code does, but instead checked all possibilities simultaneously by keeping +a list of current states and checking all of them as it advanced through the +subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA +algorithm", though it was not a traditional Finite State Machine (FSM). When +the pattern was all used up, all remaining states were possible matches, and +the one matching the longest subset of the subject string was chosen. This did +not necessarily maximize the individual wild portions of the pattern, as is +expected in Unix and Perl-style regular expressions. + +Historical note 2 +----------------- + +By contrast, the code originally written by Henry Spencer (which was +subsequently heavily modified for Perl) compiles the expression twice: once in +a dummy mode in order to find out how much store will be needed, and then for +real. (The Perl version probably doesn't do this any more; I'm talking about +the original library.) The execution function operates by backtracking and +maximizing (or, optionally, minimizing in Perl) the amount of the subject that +matches individual wild portions of the pattern. This is an "NFA algorithm" in +Friedl's terminology. + +OK, here's the real stuff +------------------------- + +For the set of functions that form the "basic" PCRE library (which are +unrelated to those mentioned above), I tried at first to invent an algorithm +that used an amount of store bounded by a multiple of the number of characters +in the pattern, to save on compiling time. However, because of the greater +complexity in Perl regular expressions, I couldn't do this. In any case, a +first pass through the pattern is helpful for other reasons. + +Computing the memory requirement: how it was +-------------------------------------------- + +Up to and including release 6.7, PCRE worked by running a very degenerate first +pass to calculate a maximum store size, and then a second pass to do the real +compile - which might use a bit less than the predicted amount of memory. The +idea was that this would turn out faster than the Henry Spencer code because +the first pass is degenerate and the second pass can just store stuff straight +into the vector, which it knows is big enough. + +Computing the memory requirement: how it is +------------------------------------------- + +By the time I was working on a potential 6.8 release, the degenerate first pass +had become very complicated and hard to maintain. Indeed one of the early +things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then +I had a flash of inspiration as to how I could run the real compile function in +a "fake" mode that enables it to compute how much memory it would need, while +actually only ever using a few hundred bytes of working memory, and without too +many tests of the mode that might slow it down. So I re-factored the compiling +functions to work this way. This got rid of about 600 lines of source. It +should make future maintenance and development easier. As this was such a major +change, I never released 6.8, instead upping the number to 7.0 (other quite +major changes are also present in the 7.0 release). + +A side effect of this work is that the previous limit of 200 on the nesting +depth of parentheses was removed. However, there is a downside: pcre_compile() +runs more slowly than before (30% or more, depending on the pattern) because it +is doing a full analysis of the pattern. My hope is that this is not a big +issue. + +Traditional matching function +----------------------------- + +The "traditional", and original, matching function is called pcre_exec(), and +it implements an NFA algorithm, similar to the original Henry Spencer algorithm +and the way that Perl works. Not surprising, since it is intended to be as +compatible with Perl as possible. This is the function most users of PCRE will +use most of the time. + +Supplementary matching function +------------------------------- + +From PCRE 6.0, there is also a supplementary matching function called +pcre_dfa_exec(). This implements a DFA matching algorithm that searches +simultaneously for all possible matches that start at one point in the subject +string. (Going back to my roots: see Historical Note 1 above.) This function +intreprets the same compiled pattern data as pcre_exec(); however, not all the +facilities are available, and those that are do not always work in quite the +same way. See the user documentation for details. + +The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, +because it may have a number of states active at one time. More work would be +needed at compile time to produce a traditional FSM where only one state is +ever active at once. I believe some other regex matchers work this way. + + +Format of compiled patterns +--------------------------- + +The compiled form of a pattern is a vector of bytes, containing items of +variable length. The first byte in an item is an opcode, and the length of the +item is either implicit in the opcode or contained in the data bytes that +follow it. + +In many cases below LINK_SIZE data values are specified for offsets within the +compiled pattern. The default value for LINK_SIZE is 2, but PCRE can be +compiled to use 3-byte or 4-byte values for these offsets (impairing the +performance). This is necessary only when patterns whose compiled length is +greater than 64K are going to be processed. In this description, we assume the +"normal" compilation options. Data values that are counts (e.g. for +quantifiers) are always just two bytes long. + +A list of the opcodes follows: + +Opcodes with no following data +------------------------------ + +These items are all just one byte long + + OP_END end of pattern + OP_ANY match any one character other than newline + OP_ALLANY match any one character, including newline + OP_ANYBYTE match any single byte, even in UTF-8 mode + OP_SOD match start of data: \A + OP_SOM, start of match (subject + offset): \G + OP_SET_SOM, set start of match (\K) + OP_CIRC ^ (start of data, or after \n in multiline) + OP_NOT_WORD_BOUNDARY \W + OP_WORD_BOUNDARY \w + OP_NOT_DIGIT \D + OP_DIGIT \d + OP_NOT_HSPACE \H + OP_HSPACE \h + OP_NOT_WHITESPACE \S + OP_WHITESPACE \s + OP_NOT_VSPACE \V + OP_VSPACE \v + OP_NOT_WORDCHAR \W + OP_WORDCHAR \w + OP_EODN match end of data or \n at end: \Z + OP_EOD match end of data: \z + OP_DOLL $ (end of data, or before \n in multiline) + OP_EXTUNI match an extended Unicode character + OP_ANYNL match any Unicode newline sequence + + OP_ACCEPT ) + OP_COMMIT ) + OP_FAIL ) These are Perl 5.10's "backtracking + OP_PRUNE ) control verbs". + OP_SKIP ) + OP_THEN ) + + +Repeating single characters +--------------------------- + +The common repeats (*, +, ?) when applied to a single character use the +following opcodes: + + OP_STAR + OP_MINSTAR + OP_POSSTAR + OP_PLUS + OP_MINPLUS + OP_POSPLUS + OP_QUERY + OP_MINQUERY + OP_POSQUERY + +In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. +Those with "MIN" in their name are the minimizing versions. Those with "POS" in +their names are possessive versions. Each is followed by the character that is +to be repeated. Other repeats make use of + + OP_UPTO + OP_MINUPTO + OP_POSUPTO + OP_EXACT + +which are followed by a two-byte count (most significant first) and the +repeated character. OP_UPTO matches from 0 to the given number. A repeat with a +non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an +OP_UPTO (or OP_MINUPTO or OPT_POSUPTO). + + +Repeating character types +------------------------- + +Repeats of things like \d are done exactly as for single characters, except +that instead of a character, the opcode for the type is stored in the data +byte. The opcodes are: + + OP_TYPESTAR + OP_TYPEMINSTAR + OP_TYPEPOSSTAR + OP_TYPEPLUS + OP_TYPEMINPLUS + OP_TYPEPOSPLUS + OP_TYPEQUERY + OP_TYPEMINQUERY + OP_TYPEPOSQUERY + OP_TYPEUPTO + OP_TYPEMINUPTO + OP_TYPEPOSUPTO + OP_TYPEEXACT + + +Match by Unicode property +------------------------- + +OP_PROP and OP_NOTPROP are used for positive and negative matches of a +character by testing its Unicode property (the \p and \P escape sequences). +Each is followed by two bytes that encode the desired property as a type and a +value. + +Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by +three bytes: OP_PROP or OP_NOTPROP and then the desired property type and +value. + + +Matching literal characters +--------------------------- + +The OP_CHAR opcode is followed by a single character that is to be matched +casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the +character may be more than one byte long. (Earlier versions of PCRE used +multi-character strings, but this was changed to allow some new features to be +added.) + + +Character classes +----------------- + +If there is only one character, OP_CHAR or OP_CHARNC is used for a positive +class, and OP_NOT for a negative one (that is, for something like [^a]). +However, in UTF-8 mode, the use of OP_NOT applies only to characters with +values < 128, because OP_NOT is confined to single bytes. + +Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, +negated, single-character class. The normal ones (OP_STAR etc.) are used for a +repeated positive single-character class. + +When there's more than one character in a class and all the characters are less +than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative +one. In either case, the opcode is followed by a 32-byte bit map containing a 1 +bit for every character that is acceptable. The bits are counted from the least +significant end of each byte. + +The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, +subject characters with values greater than 256 can be handled correctly. For +OP_CLASS they don't match, whereas for OP_NCLASS they do. + +For classes containing characters with values > 255, OP_XCLASS is used. It +optionally uses a bit map (if any characters lie within it), followed by a list +of pairs and single characters. There is a flag character than indicates +whether it's a positive or a negative class. + + +Back references +--------------- + +OP_REF is followed by two bytes containing the reference number. + + +Repeating character classes and back references +----------------------------------------------- + +Single-character classes are handled specially (see above). This section +applies to OP_CLASS and OP_REF. In both cases, the repeat information follows +the base item. The matching code looks at the following opcode to see if it is +one of + + OP_CRSTAR + OP_CRMINSTAR + OP_CRPLUS + OP_CRMINPLUS + OP_CRQUERY + OP_CRMINQUERY + OP_CRRANGE + OP_CRMINRANGE + +All but the last two are just single-byte items. The others are followed by +four bytes of data, comprising the minimum and maximum repeat counts. There are +no special possessive opcodes for these repeats; a possessive repeat is +compiled into an atomic group. + + +Brackets and alternation +------------------------ + +A pair of non-capturing (round) brackets is wrapped round each expression at +compile time, so alternation always happens in the context of brackets. + +[Note for North Americans: "bracket" to some English speakers, including +myself, can be round, square, curly, or pointy. Hence this usage.] + +Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99 +capturing brackets and it used a different opcode for each one. From release +3.5, the limit was removed by putting the bracket number into the data for +higher-numbered brackets. From release 7.0 all capturing brackets are handled +this way, using the single opcode OP_CBRA. + +A bracket opcode is followed by LINK_SIZE bytes which give the offset to the +next alternative OP_ALT or, if there aren't any branches, to the matching +OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to +the next one, or to the OP_KET opcode. For capturing brackets, the bracket +number immediately follows the offset, always as a 2-byte item. + +OP_KET is used for subpatterns that do not repeat indefinitely, while +OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or +maximally respectively. All three are followed by LINK_SIZE bytes giving (as a +positive number) the offset back to the matching bracket opcode. + +If a subpattern is quantified such that it is permitted to match zero times, it +is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are +single-byte opcodes that tell the matcher that skipping the following +subpattern entirely is a valid branch. In the case of the first two, not +skipping the pattern is also valid (greedy and non-greedy). The third is used +when a pattern has the quantifier {0,0}. It cannot be entirely discarded, +because it may be called as a subroutine from elsewhere in the regex. + +A subpattern with an indefinite maximum repetition is replicated in the +compiled data its minimum number of times (or once with OP_BRAZERO if the +minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX +as appropriate. + +A subpattern with a bounded maximum repetition is replicated in a nested +fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO +before each replication after the minimum, so that, for example, (abc){2,5} is +compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group +has the same number. + +When a repeated subpattern has an unbounded upper limit, it is checked to see +whether it could match an empty string. If this is the case, the opcode in the +final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher +that it needs to check for matching an empty string when it hits OP_KETRMIN or +OP_KETRMAX, and if so, to break the loop. + + +Assertions +---------- + +Forward assertions are just like other subpatterns, but starting with one of +the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes +OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion +is OP_REVERSE, followed by a two byte count of the number of characters to move +back the pointer in the subject string. When operating in UTF-8 mode, the count +is a character count rather than a byte count. A separate count is present in +each alternative of a lookbehind assertion, allowing them to have different +fixed lengths. + + +Once-only (atomic) subpatterns +------------------------------ + +These are also just like other subpatterns, but they start with the opcode +OP_ONCE. The check for matching an empty string in an unbounded repeat is +handled entirely at runtime, so there is just this one opcode. + + +Conditional subpatterns +----------------------- + +These are like other subpatterns, but they start with the opcode OP_COND, or +OP_SCOND for one that might match an empty string in an unbounded repeat. If +the condition is a back reference, this is stored at the start of the +subpattern using the opcode OP_CREF followed by two bytes containing the +reference number. If the condition is "in recursion" (coded as "(?(R)"), or "in +recursion of group x" (coded as "(?(Rx)"), the group number is stored at the +start of the subpattern using the opcode OP_RREF, and a value of zero for "the +whole pattern". For a DEFINE condition, just the single byte OP_DEF is used (it +has no associated data). Otherwise, a conditional subpattern always starts with +one of the assertions. + + +Recursion +--------- + +Recursion either matches the current regex, or some subexpression. The opcode +OP_RECURSE is followed by an value which is the offset to the starting bracket +from the start of the whole pattern. From release 6.5, OP_RECURSE is +automatically wrapped inside OP_ONCE brackets (because otherwise some patterns +broke it). OP_RECURSE is also used for "subroutine" calls, even though they +are not strictly a recursion. + + +Callout +------- + +OP_CALLOUT is followed by one byte of data that holds a callout number in the +range 0 to 254 for manual callouts, or 255 for an automatic callout. In both +cases there follows a two-byte value giving the offset in the pattern to the +start of the following item, and another two-byte item giving the length of the +next item. + + +Changing options +---------------- + +If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT +opcode is compiled, followed by one byte containing the new settings of these +flags. If there are several alternatives, there is an occurrence of OP_OPT at +the start of all those following the first options change, to set appropriate +options for the start of the alternative. Immediately after the end of the +group there is another such item to reset the flags to their previous values. A +change of flag right at the very start of the pattern can be handled entirely +at compile time, and so does not cause anything to be put into the compiled +data. + +Philip Hazel +April 2008 Modified: freeswitch/trunk/libs/pcre/INSTALL ============================================================================== --- freeswitch/trunk/libs/pcre/INSTALL (original) +++ freeswitch/trunk/libs/pcre/INSTALL Mon Jun 8 18:51:30 2009 @@ -1,41 +1,54 @@ +Installation Instructions +************************* + +Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005, +2006, 2007, 2008 Free Software Foundation, Inc. + + This file is free documentation; the Free Software Foundation gives +unlimited permission to copy, distribute and modify it. + Basic Installation ================== - These are generic installation instructions that apply to systems that -can run the `configure' shell script - Unix systems and any that imitate -it. They are not specific to PCRE. There are PCRE-specific instructions -for non-Unix systems in the file NON-UNIX-USE. + Briefly, the shell commands `./configure; make; make install' should +configure, build, and install this package. The following +more-detailed instructions are generic; see the `README' file for +instructions specific to this package. The `configure' shell script attempts to guess correct values for various system-dependent variables used during compilation. It uses those values to create a `Makefile' in each directory of the package. It may also create one or more `.h' files containing system-dependent definitions. Finally, it creates a shell script `config.status' that -you can run in the future to recreate the current configuration, a file -`config.cache' that saves the results of its tests to speed up -reconfiguring, and a file `config.log' containing compiler output -(useful mainly for debugging `configure'). +you can run in the future to recreate the current configuration, and a +file `config.log' containing compiler output (useful mainly for +debugging `configure'). + + It can also use an optional file (typically called `config.cache' +and enabled with `--cache-file=config.cache' or simply `-C') that saves +the results of its tests to speed up reconfiguring. Caching is +disabled by default to prevent problems with accidental use of stale +cache files. If you need to do unusual things to compile the package, please try to figure out how `configure' could check whether to do them, and mail diffs or instructions to the address given in the `README' so they can -be considered for the next release. If at some point `config.cache' -contains results you don't want to keep, you may remove or edit it. - - The file `configure.in' is used to create `configure' by a program -called `autoconf'. You only need `configure.in' if you want to change -it or regenerate `configure' using a newer version of `autoconf'. +be considered for the next release. If you are using the cache, and at +some point `config.cache' contains results you don't want to keep, you +may remove or edit it. + + The file `configure.ac' (or `configure.in') is used to create +`configure' by a program called `autoconf'. You need `configure.ac' if +you want to change it or regenerate `configure' using a newer version +of `autoconf'. The simplest way to compile this package is: 1. `cd' to the directory containing the package's source code and type - `./configure' to configure the package for your system. If you're - using `csh' on an old version of System V, you might need to type - `sh ./configure' instead to prevent `csh' from trying to execute - `configure' itself. + `./configure' to configure the package for your system. - Running `configure' takes awhile. While running, it prints some - messages telling which features it is checking for. + Running `configure' might take a while. While running, it prints + some messages telling which features it is checking for. 2. Type `make' to compile the package. @@ -54,52 +67,69 @@ all sorts of other programs in order to regenerate files that came with the distribution. + 6. Often, you can also type `make uninstall' to remove the installed + files again. + Compilers and Options ===================== Some systems require unusual options for compilation or linking that -the `configure' script does not know about. You can give `configure' -initial values for variables by setting them in the environment. Using -a Bourne-compatible shell, you can do that on the command line like -this: - CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure +the `configure' script does not know about. Run `./configure --help' +for details on some of the pertinent environment variables. -Or on systems that have the `env' program, you can do it like this: - env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure + You can give `configure' initial values for configuration parameters +by setting variables in the command line or in the environment. Here +is an example: + + ./configure CC=c99 CFLAGS=-g LIBS=-lposix + + *Note Defining Variables::, for more details. Compiling For Multiple Architectures ==================================== You can compile the package for more than one kind of computer at the same time, by placing the object files for each architecture in their -own directory. To do this, you must use a version of `make' that -supports the `VPATH' variable, such as GNU `make'. `cd' to the +own directory. To do this, you can use GNU `make'. `cd' to the directory where you want the object files and executables to go and run the `configure' script. `configure' automatically checks for the source code in the directory that `configure' is in and in `..'. - If you have to use a `make' that does not supports the `VPATH' -variable, you have to compile the package for one architecture at a time -in the source code directory. After you have installed the package for -one architecture, use `make distclean' before reconfiguring for another -architecture. + With a non-GNU `make', it is safer to compile the package for one +architecture at a time in the source code directory. After you have +installed the package for one architecture, use `make distclean' before +reconfiguring for another architecture. + + On MacOS X 10.5 and later systems, you can create libraries and +executables that work on multiple system types--known as "fat" or +"universal" binaries--by specifying multiple `-arch' options to the +compiler but only a single `-arch' option to the preprocessor. Like +this: + + ./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ + CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ + CPP="gcc -E" CXXCPP="g++ -E" + + This is not guaranteed to produce working output in all cases, you +may have to build one architecture at a time and combine the results +using the `lipo' tool if you have problems. Installation Names ================== - By default, `make install' will install the package's files in -`/usr/local/bin', `/usr/local/man', etc. You can specify an -installation prefix other than `/usr/local' by giving `configure' the -option `--prefix=PATH'. + By default, `make install' installs the package's commands under +`/usr/local/bin', include files under `/usr/local/include', etc. You +can specify an installation prefix other than `/usr/local' by giving +`configure' the option `--prefix=PREFIX'. You can specify separate installation prefixes for architecture-specific files and architecture-independent files. If you -give `configure' the option `--exec-prefix=PATH', the package will use -PATH as the prefix for installing programs and libraries. -Documentation and other data files will still use the regular prefix. +pass the option `--exec-prefix=PREFIX' to `configure', the package uses +PREFIX as the prefix for installing programs and libraries. +Documentation and other data files still use the regular prefix. In addition, if you use an unusual directory layout you can give -options like `--bindir=PATH' to specify different values for particular +options like `--bindir=DIR' to specify different values for particular kinds of files. Run `configure --help' for a list of the directories you can set and what kinds of files go in them. @@ -122,25 +152,57 @@ you can use the `configure' options `--x-includes=DIR' and `--x-libraries=DIR' to specify their locations. +Particular systems +================== + + On HP-UX, the default C compiler is not ANSI C compatible. If GNU +CC is not installed, it is recommended to use the following options in +order to use an ANSI C compiler: + + ./configure CC="cc -Ae" + +and if that doesn't work, install pre-built binaries of GCC for HP-UX. + + On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot +parse its `<wchar.h>' header file. The option `-nodtk' can be used as +a workaround. If GNU CC is not installed, it is therefore recommended +to try + + ./configure CC="cc" + +and if that doesn't work, try + + ./configure CC="cc -nodtk" + Specifying the System Type ========================== - There may be some features `configure' can not figure out -automatically, but needs to determine by the type of host the package -will run on. Usually `configure' can figure that out, but if it prints -a message saying it can not guess the host type, give it the -`--host=TYPE' option. TYPE can either be a short name for the system -type, such as `sun4', or a canonical name with three fields: + There may be some features `configure' cannot figure out +automatically, but needs to determine by the type of machine the package +will run on. Usually, assuming the package is built to be run on the +_same_ architectures, `configure' can figure that out, but if it prints +a message saying it cannot guess the machine type, give it the +`--build=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name which has the form: + CPU-COMPANY-SYSTEM -See the file `config.sub' for the possible values of each field. If +where SYSTEM can have one of these forms: + + OS KERNEL-OS + + See the file `config.sub' for the possible values of each field. If `config.sub' isn't included in this package, then this package doesn't -need to know the host type. +need to know the machine type. - If you are building compiler tools for cross-compiling, you can also -use the `--target=TYPE' option to select the type of system they will -produce code for and the `--build=TYPE' option to select the type of -system on which you are compiling the package. + If you are _building_ compiler tools for cross-compiling, you should +use the option `--target=TYPE' to select the type of system they will +produce code for. + + If you want to _use_ a cross compiler, that generates code for a +platform different from the build platform, you should specify the +"host" platform (i.e., that on which the generated programs will +eventually be run) with `--host=TYPE'. Sharing Defaults ================ @@ -153,19 +215,55 @@ `CONFIG_SITE' environment variable to the location of the site script. A warning: not all `configure' scripts look for a site script. -Operation Controls +Defining Variables ================== + Variables not defined in a site shell script can be set in the +environment passed to `configure'. However, some packages may run +configure again during the build, and the customized values of these +variables may be lost. In order to avoid this problem, you should set +them in the `configure' command line, using `VAR=value'. For example: + + ./configure CC=/usr/local2/bin/gcc + +causes the specified `gcc' to be used as the C compiler (unless it is +overridden in the site shell script). + +Unfortunately, this technique does not work for `CONFIG_SHELL' due to +an Autoconf bug. Until the bug is fixed you can use this workaround: + + CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash + +`configure' Invocation +====================== + `configure' recognizes the following options to control how it operates. -`--cache-file=FILE' - Use and save the results of the tests in FILE instead of - `./config.cache'. Set FILE to `/dev/null' to disable caching, for - debugging `configure'. - `--help' - Print a summary of the options to `configure', and exit. +`-h' + Print a summary of all of the options to `configure', and exit. + +`--help=short' +`--help=recursive' + Print a summary of the options unique to this package's + `configure', and exit. The `short' variant lists options used + only in the top level, while the `recursive' variant lists options + also present in any nested packages. + +`--version' +`-V' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`--cache-file=FILE' + Enable the cache: use and save the results of the tests in FILE, + traditionally `config.cache'. FILE defaults to `/dev/null' to + disable caching. + +`--config-cache' +`-C' + Alias for `--cache-file=config.cache'. `--quiet' `--silent' @@ -178,9 +276,16 @@ Look for the package's source code in directory DIR. Usually `configure' can determine that directory automatically. -`--version' - Print the version of Autoconf used to generate the `configure' - script, and exit. +`--prefix=DIR' + Use DIR as the installation prefix. *Note Installation Names:: + for more details, including other options available for fine-tuning + the installation locations. + +`--no-create' +`-n' + Run the configure checks, but stop before creating any output + files. + +`configure' also accepts some other, not widely useful, options. Run +`configure --help' for more details. -`configure' also accepts some other, not widely useful, options. - \ No newline at end of file Modified: freeswitch/trunk/libs/pcre/LICENCE ============================================================================== --- freeswitch/trunk/libs/pcre/LICENCE (original) +++ freeswitch/trunk/libs/pcre/LICENCE Mon Jun 8 18:51:30 2009 @@ -4,7 +4,7 @@ PCRE is a library of functions to support regular expressions whose syntax and semantics are as close as possible to those of the Perl 5 language. -Release 6 of PCRE is distributed under the terms of the "BSD" licence, as +Release 7 of PCRE is distributed under the terms of the "BSD" licence, as specified below. The documentation for PCRE, supplied in the "doc" directory, is distributed under the same terms as the software itself. @@ -20,9 +20,9 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. +Cambridge, England. -Copyright (c) 1997-2006 University of Cambridge +Copyright (c) 1997-2009 University of Cambridge All rights reserved. @@ -31,7 +31,7 @@ Contributed by: Google Inc. -Copyright (c) 2006, Google Inc. +Copyright (c) 2007-2008, Google Inc. All rights reserved. Added: freeswitch/trunk/libs/pcre/Makefile.am ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/Makefile.am Mon Jun 8 18:51:30 2009 @@ -0,0 +1,390 @@ +## Process this file with automake to produce Makefile.in. + +dist_doc_DATA = \ + doc/pcre.txt \ + doc/pcre-config.txt \ + doc/pcregrep.txt \ + doc/pcretest.txt \ + AUTHORS \ + COPYING \ + ChangeLog \ + LICENCE \ + NEWS \ + README + +dist_html_DATA = \ + doc/html/index.html \ + doc/html/pcre.html \ + doc/html/pcre-config.html \ + doc/html/pcre_compile.html \ + doc/html/pcre_compile2.html \ + doc/html/pcre_config.html \ + doc/html/pcre_copy_named_substring.html \ + doc/html/pcre_copy_substring.html \ + doc/html/pcre_dfa_exec.html \ + doc/html/pcre_exec.html \ + doc/html/pcre_free_substring.html \ + doc/html/pcre_free_substring_list.html \ + doc/html/pcre_fullinfo.html \ + doc/html/pcre_get_named_substring.html \ + doc/html/pcre_get_stringnumber.html \ + doc/html/pcre_get_stringtable_entries.html \ + doc/html/pcre_get_substring.html \ + doc/html/pcre_get_substring_list.html \ + doc/html/pcre_info.html \ + doc/html/pcre_maketables.html \ + doc/html/pcre_refcount.html \ + doc/html/pcre_study.html \ + doc/html/pcre_version.html \ + doc/html/pcreapi.html \ + doc/html/pcrebuild.html \ + doc/html/pcrecallout.html \ + doc/html/pcrecompat.html \ + doc/html/pcregrep.html \ + doc/html/pcrematching.html \ + doc/html/pcrepartial.html \ + doc/html/pcrepattern.html \ + doc/html/pcreperform.html \ + doc/html/pcreposix.html \ + doc/html/pcreprecompile.html \ + doc/html/pcresample.html \ + doc/html/pcrestack.html \ + doc/html/pcresyntax.html \ + doc/html/pcretest.html + +pcrecpp_html = doc/html/pcrecpp.html +dist_noinst_DATA = $(pcrecpp_html) + +if WITH_PCRE_CPP +html_DATA = $(pcrecpp_html) +endif + +# The Libtool libraries to install. We'll add to this later. +lib_LTLIBRARIES = + +# Unit tests you want to run when people type 'make check'. +# TESTS is for binary unit tests, check_SCRIPTS for script-based tests +TESTS = +check_SCRIPTS = +dist_noinst_SCRIPTS = + +# Some of the binaries we make are to be installed, and others are +# (non-user-visible) helper programs needed to build libpcre. +bin_PROGRAMS = +noinst_PROGRAMS = + +# Additional files to delete on 'make clean' and 'make maintainer-clean'. +CLEANFILES = +MAINTAINERCLEANFILES = + +# Additional files to bundle with the distribution, over and above what +# the Autotools include by default. +EXTRA_DIST = + +# These files contain maintenance information +EXTRA_DIST += \ + doc/perltest.txt \ + NON-UNIX-USE \ + HACKING + +# These files are used in the preparation of a release +EXTRA_DIST += \ + PrepareRelease \ + CleanTxt \ + Detrail \ + 132html \ + doc/index.html.src + +# These files are to do with building for Virtual Pascal +EXTRA_DIST += \ + makevp.bat \ + makevp_c.txt \ + makevp_l.txt \ + pcregexp.pas + +# These files are usable versions of pcre.h and config.h that are distributed +# for the benefit of people who are building PCRE manually, without the +# Autotools support. +EXTRA_DIST += \ + pcre.h.generic \ + config.h.generic + +pcre.h.generic: configure.ac + rm -f $@ + cp -p pcre.h $@ + +MAINTAINERCLEANFILES += pcre.h.generic + +# These are the header files we'll install. We do not distribute pcre.h because +# it is generated from pcre.h.in. +nodist_include_HEADERS = \ + pcre.h +include_HEADERS = \ + pcreposix.h + +# These additional headers will be be installed if C++ support is enabled. We +# do not distribute pcrecpparg.h or pcre_stringpiece.h, as these are generated +# from corresponding .h.in files (which we do distribute). +if WITH_PCRE_CPP +nodist_include_HEADERS += \ + pcrecpparg.h \ + pcre_stringpiece.h +include_HEADERS += \ + pcrecpp.h \ + pcre_scanner.h +endif # WITH_PCRE_CPP + +bin_SCRIPTS = pcre-config + +## --------------------------------------------------------------- +## The dftables program is used to rebuild character tables before compiling +## PCRE, if --enable-rebuild-chartables is specified. It is not a user-visible +## program. The default (when --enable-rebuild-chartables is not specified) is +## to copy a distributed set of tables that are defined for ASCII code. In this +## case, dftables is not needed. + +if WITH_REBUILD_CHARTABLES + +noinst_PROGRAMS += dftables +dftables_SOURCES = dftables.c + +pcre_chartables.c: dftables$(EXEEXT) + ./dftables$(EXEEXT) $@ +else + +pcre_chartables.c: $(srcdir)/pcre_chartables.c.dist + rm -f $@ + $(LN_S) $(srcdir)/pcre_chartables.c.dist $@ + +endif # WITH_REBUILD_CHARTABLES + + +## The main pcre library +lib_LTLIBRARIES += libpcre.la +libpcre_la_SOURCES = \ + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_internal.h \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucd.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + ucp.h + +## This file is generated as part of the building process, so don't distribute. +nodist_libpcre_la_SOURCES = \ + pcre_chartables.c + +# The pcre_printint.src file is #included by some source files, so it must be +# distributed. The pcre_chartables.c.dist file is the default version of +# pcre_chartables.c, used unless --enable-rebuild-chartables is specified. +EXTRA_DIST += pcre_printint.src pcre_chartables.c.dist + +libpcre_la_LDFLAGS = $(EXTRA_LIBPCRE_LDFLAGS) + +CLEANFILES += pcre_chartables.c + +## A version of the main pcre library that has a posix re API. +lib_LTLIBRARIES += libpcreposix.la +libpcreposix_la_SOURCES = \ + pcreposix.c +libpcreposix_la_LDFLAGS = $(EXTRA_LIBPCREPOSIX_LDFLAGS) +libpcreposix_la_LIBADD = libpcre.la + +## There's a C++ library as well. +if WITH_PCRE_CPP + +lib_LTLIBRARIES += libpcrecpp.la +libpcrecpp_la_SOURCES = \ + pcrecpp_internal.h \ + pcrecpp.cc \ + pcre_scanner.cc \ + pcre_stringpiece.cc +libpcrecpp_la_LDFLAGS = $(EXTRA_LIBPCRECPP_LDFLAGS) +libpcrecpp_la_LIBADD = libpcre.la + +TESTS += pcrecpp_unittest +noinst_PROGRAMS += pcrecpp_unittest +pcrecpp_unittest_SOURCES = pcrecpp_unittest.cc +pcrecpp_unittest_LDADD = libpcrecpp.la + +TESTS += pcre_scanner_unittest +noinst_PROGRAMS += pcre_scanner_unittest +pcre_scanner_unittest_SOURCES = pcre_scanner_unittest.cc +pcre_scanner_unittest_LDADD = libpcrecpp.la + +TESTS += pcre_stringpiece_unittest +noinst_PROGRAMS += pcre_stringpiece_unittest +pcre_stringpiece_unittest_SOURCES = pcre_stringpiece_unittest.cc +pcre_stringpiece_unittest_LDADD = libpcrecpp.la + +endif # WITH_PCRE_CPP + +## The main unit tests + +# Each unit test is a binary plus a script that runs that binary in various +# ways. We install these test binaries in case folks find it helpful. + +TESTS += RunTest +dist_noinst_SCRIPTS += RunTest +EXTRA_DIST += RunTest.bat +bin_PROGRAMS += pcretest +pcretest_SOURCES = pcretest.c +pcretest_LDADD = libpcreposix.la $(LIBREADLINE) + +TESTS += RunGrepTest +dist_noinst_SCRIPTS += RunGrepTest +bin_PROGRAMS += pcregrep +pcregrep_SOURCES = pcregrep.c +pcregrep_LDADD = libpcreposix.la $(LIBZ) $(LIBBZ2) + +EXTRA_DIST += \ + testdata/grepinput \ + testdata/grepinput8 \ + testdata/grepinputv \ + testdata/grepinputx \ + testdata/greplist \ + testdata/grepoutput \ + testdata/grepoutput8 \ + testdata/grepoutputN \ + testdata/testinput1 \ + testdata/testinput2 \ + testdata/testinput3 \ + testdata/testinput4 \ + testdata/testinput5 \ + testdata/testinput6 \ + testdata/testinput7 \ + testdata/testinput8 \ + testdata/testinput9 \ + testdata/testinput10 \ + testdata/testoutput1 \ + testdata/testoutput2 \ + testdata/testoutput3 \ + testdata/testoutput4 \ + testdata/testoutput5 \ + testdata/testoutput6 \ + testdata/testoutput7 \ + testdata/testoutput8 \ + testdata/testoutput9 \ + testdata/testoutput10 \ + testdata/wintestinput3 \ + testdata/wintestoutput3 \ + perltest.pl + +CLEANFILES += \ + testsavedregex \ + teststderr \ + testtry \ + testNinput + + +# PCRE demonstration program. No longer built automatcally. The point is that +# the users should build it themselves. So just distribute the source. +# noinst_PROGRAMS += pcredemo +# pcredemo_SOURCES = pcredemo.c +# pcredemo_LDADD = libpcre.la + +EXTRA_DIST += pcredemo.c + + +## Utility rules, documentation, etc. + +# A compatibility line, the old build system worked with 'make test' +test: check ; + + +# A PCRE user submitted the following addition, saying that it "will allow +# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a +# nice DLL for Windows use". (It is used by the pcre.dll target.) +DLL_OBJS= pcre_compile.o pcre_config.o \ + pcre_dfa_exec.o pcre_exec.o pcre_fullinfo.o pcre_get.o \ + pcre_globals.o pcre_info.o pcre_maketables.o \ + pcre_newline.o pcre_ord2utf8.o pcre_refcount.o \ + pcre_study.o pcre_tables.o pcre_try_flipped.o \ + pcre_ucd.o pcre_valid_utf8.o pcre_version.o \ + pcre_chartables.o \ + pcre_xclass.o + +# A PCRE user submitted the following addition, saying that it "will allow +# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a +# nice DLL for Windows use". +pcre.dll: $(DLL_OBJS) + $(CC) -shared -o pcre.dll -Wl,"--strip-all" -Wl,"--export-all-symbols" $(DLL_OBJS) + + +# We have .pc files for pkg-config users. +pkgconfigdir = $(libdir)/pkgconfig +pkgconfig_DATA = libpcre.pc +if WITH_PCRE_CPP +pkgconfig_DATA += libpcrecpp.pc +endif + +dist_man_MANS = \ + doc/pcre.3 \ + doc/pcre-config.1 \ + doc/pcre_compile.3 \ + doc/pcre_compile2.3 \ + doc/pcre_config.3 \ + doc/pcre_copy_named_substring.3 \ + doc/pcre_copy_substring.3 \ + doc/pcre_dfa_exec.3 \ + doc/pcre_exec.3 \ + doc/pcre_free_substring.3 \ + doc/pcre_free_substring_list.3 \ + doc/pcre_fullinfo.3 \ + doc/pcre_get_named_substring.3 \ + doc/pcre_get_stringnumber.3 \ + doc/pcre_get_stringtable_entries.3 \ + doc/pcre_get_substring.3 \ + doc/pcre_get_substring_list.3 \ + doc/pcre_info.3 \ + doc/pcre_maketables.3 \ + doc/pcre_refcount.3 \ + doc/pcre_study.3 \ + doc/pcre_version.3 \ + doc/pcreapi.3 \ + doc/pcrebuild.3 \ + doc/pcrecallout.3 \ + doc/pcrecompat.3 \ + doc/pcregrep.1 \ + doc/pcrematching.3 \ + doc/pcrepartial.3 \ + doc/pcrepattern.3 \ + doc/pcreperform.3 \ + doc/pcreposix.3 \ + doc/pcreprecompile.3 \ + doc/pcresample.3 \ + doc/pcrestack.3 \ + doc/pcresyntax.3 \ + doc/pcretest.1 + +pcrecpp_man = doc/pcrecpp.3 +EXTRA_DIST += $(pcrecpp_man) + +if WITH_PCRE_CPP +man_MANS = $(pcrecpp_man) +endif + +## CMake support + +EXTRA_DIST += \ + cmake/COPYING-CMAKE-SCRIPTS \ + cmake/FindPackageHandleStandardArgs.cmake \ + cmake/FindReadline.cmake \ + CMakeLists.txt \ + config-cmake.h.in + +## end Makefile.am Modified: freeswitch/trunk/libs/pcre/Makefile.in ============================================================================== --- freeswitch/trunk/libs/pcre/Makefile.in (original) +++ freeswitch/trunk/libs/pcre/Makefile.in Mon Jun 8 18:51:30 2009 @@ -1,606 +1,1430 @@ +# Makefile.in generated by automake 1.10 from Makefile.am. +# @configure_input@ -# Makefile.in for PCRE (Perl-Compatible Regular Expression) library. +# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, +# 2003, 2004, 2005, 2006 Free Software Foundation, Inc. +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ -############################################################################# -# PCRE is developed on a Unix system. I do not use Windows or Macs, and know -# nothing about building software on them. Although the code of PCRE should -# be very portable, the building system in this Makefile is designed for Unix -# systems. However, there are features that have been supplied to me by various -# people that should make it work on MinGW and Cygwin systems. -# This setting enables Unix-style directory scanning in pcregrep, triggered -# by the -f option. Maybe one day someone will add code for other systems. - -PCREGREP_OSTYPE=-DIS_UNIX - -############################################################################# - - -# Libtool places .o files in the .libs directory; this can mean that "make" -# thinks is it not up-to-date when in fact it is. This setting helps when -# GNU "make" is being used. It presumably does no harm in other cases. - -VPATH=.libs - - -#---------------------------------------------------------------------------# -# The following lines are modified by "configure" to insert data that it is # -# given in its arguments, or which it finds out for itself. # -#---------------------------------------------------------------------------# - -SHELL = @SHELL@ -prefix = @prefix@ -exec_prefix = @exec_prefix@ -top_srcdir = @top_srcdir@ +VPATH = @srcdir@ +pkgdatadir = $(datadir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +TESTS = $(am__EXEEXT_2) RunTest RunGrepTest +bin_PROGRAMS = pcretest$(EXEEXT) pcregrep$(EXEEXT) +noinst_PROGRAMS = $(am__EXEEXT_1) $(am__EXEEXT_2) + +# These additional headers will be be installed if C++ support is enabled. We +# do not distribute pcrecpparg.h or pcre_stringpiece.h, as these are generated +# from corresponding .h.in files (which we do distribute). +@WITH_PCRE_CPP_TRUE@am__append_1 = \ +@WITH_PCRE_CPP_TRUE@ pcrecpparg.h \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece.h + +@WITH_PCRE_CPP_TRUE@am__append_2 = \ +@WITH_PCRE_CPP_TRUE@ pcrecpp.h \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner.h + +@WITH_REBUILD_CHARTABLES_TRUE@am__append_3 = dftables +@WITH_PCRE_CPP_TRUE@am__append_4 = libpcrecpp.la +@WITH_PCRE_CPP_TRUE@am__append_5 = pcrecpp_unittest \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner_unittest \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece_unittest +@WITH_PCRE_CPP_TRUE@am__append_6 = pcrecpp_unittest \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner_unittest \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece_unittest +@WITH_PCRE_CPP_TRUE@am__append_7 = libpcrecpp.pc +subdir = . +DIST_COMMON = README $(am__configure_deps) $(am__include_HEADERS_DIST) \ + $(dist_doc_DATA) $(dist_html_DATA) $(dist_man_MANS) \ + $(dist_noinst_DATA) $(dist_noinst_SCRIPTS) \ + $(srcdir)/Makefile.am $(srcdir)/Makefile.in \ + $(srcdir)/config.h.in $(srcdir)/libpcre.pc.in \ + $(srcdir)/libpcrecpp.pc.in $(srcdir)/pcre-config.in \ + $(srcdir)/pcre.h.in $(srcdir)/pcre_stringpiece.h.in \ + $(srcdir)/pcrecpparg.h.in $(top_srcdir)/configure AUTHORS \ + COPYING ChangeLog INSTALL NEWS config.guess config.sub depcomp \ + install-sh ltmain.sh missing mkinstalldirs +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \ + configure.lineno config.status.lineno mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs - -# NB: top_builddir is not referred to directly below, but it is used in the -# setting of $(LIBTOOL), so don't remove it! - -top_builddir = . - -# BINDIR is the directory in which the pcregrep, pcretest, and pcre-config -# commands are installed. -# INCDIR is the directory in which the public header files pcre.h and -# pcreposix.h are installed. -# LIBDIR is the directory in which the libraries are installed. -# MANDIR is the directory in which the man pages are installed. - -BINDIR = @bindir@ -LIBDIR = @libdir@ -INCDIR = @includedir@ -MANDIR = @mandir@ - -# EXEEXT is set by configure to the extention of an executable file -# OBJEXT is set by configure to the extention of an object file -# The BUILD_* equivalents are the same but for the host we're building on - -EXEEXT = @EXEEXT@ -OBJEXT = @OBJEXT@ -# Note that these are just here to have a convenient place to look at the -# outcome. -BUILD_EXEEXT = @BUILD_EXEEXT@ -BUILD_OBJEXT = @BUILD_OBJEXT@ - -# POSIX_OBJ and POSIX_LOBJ are either set empty, or to the names of the -# POSIX object files. - -POSIX_OBJ = @POSIX_OBJ@ -POSIX_LOBJ = @POSIX_LOBJ@ - -# The compiler, C flags, preprocessor flags, etc - +CONFIG_HEADER = config.h +CONFIG_CLEAN_FILES = libpcre.pc libpcrecpp.pc pcre-config pcre.h \ + pcre_stringpiece.h pcrecpparg.h +am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; +am__vpath_adj = case $$p in \ + $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \ + *) f=$$p;; \ + esac; +am__strip_dir = `echo $$p | sed -e 's|^.*/||'`; +am__installdirs = "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" \ + "$(DESTDIR)$(bindir)" "$(DESTDIR)$(man1dir)" \ + "$(DESTDIR)$(man3dir)" "$(DESTDIR)$(docdir)" \ + "$(DESTDIR)$(htmldir)" "$(DESTDIR)$(htmldir)" \ + "$(DESTDIR)$(pkgconfigdir)" "$(DESTDIR)$(includedir)" \ + "$(DESTDIR)$(includedir)" +libLTLIBRARIES_INSTALL = $(INSTALL) +LTLIBRARIES = $(lib_LTLIBRARIES) +libpcre_la_LIBADD = +am_libpcre_la_OBJECTS = pcre_compile.lo pcre_config.lo \ + pcre_dfa_exec.lo pcre_exec.lo pcre_fullinfo.lo pcre_get.lo \ + pcre_globals.lo pcre_info.lo pcre_maketables.lo \ + pcre_newline.lo pcre_ord2utf8.lo pcre_refcount.lo \ + pcre_study.lo pcre_tables.lo pcre_try_flipped.lo pcre_ucd.lo \ + pcre_valid_utf8.lo pcre_version.lo pcre_xclass.lo +nodist_libpcre_la_OBJECTS = pcre_chartables.lo +libpcre_la_OBJECTS = $(am_libpcre_la_OBJECTS) \ + $(nodist_libpcre_la_OBJECTS) +libpcre_la_LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) \ + $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ + $(libpcre_la_LDFLAGS) $(LDFLAGS) -o $@ +@WITH_PCRE_CPP_TRUE@libpcrecpp_la_DEPENDENCIES = libpcre.la +am__libpcrecpp_la_SOURCES_DIST = pcrecpp_internal.h pcrecpp.cc \ + pcre_scanner.cc pcre_stringpiece.cc +@WITH_PCRE_CPP_TRUE@am_libpcrecpp_la_OBJECTS = pcrecpp.lo \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner.lo pcre_stringpiece.lo +libpcrecpp_la_OBJECTS = $(am_libpcrecpp_la_OBJECTS) +libpcrecpp_la_LINK = $(LIBTOOL) --tag=CXX $(AM_LIBTOOLFLAGS) \ + $(LIBTOOLFLAGS) --mode=link $(CXXLD) $(AM_CXXFLAGS) \ + $(CXXFLAGS) $(libpcrecpp_la_LDFLAGS) $(LDFLAGS) -o $@ +@WITH_PCRE_CPP_TRUE@am_libpcrecpp_la_rpath = -rpath $(libdir) +libpcreposix_la_DEPENDENCIES = libpcre.la +am_libpcreposix_la_OBJECTS = pcreposix.lo +libpcreposix_la_OBJECTS = $(am_libpcreposix_la_OBJECTS) +libpcreposix_la_LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) \ + $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ + $(libpcreposix_la_LDFLAGS) $(LDFLAGS) -o $@ +binPROGRAMS_INSTALL = $(INSTALL_PROGRAM) +@WITH_REBUILD_CHARTABLES_TRUE@am__EXEEXT_1 = dftables$(EXEEXT) +@WITH_PCRE_CPP_TRUE@am__EXEEXT_2 = pcrecpp_unittest$(EXEEXT) \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner_unittest$(EXEEXT) \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece_unittest$(EXEEXT) +PROGRAMS = $(bin_PROGRAMS) $(noinst_PROGRAMS) +am__dftables_SOURCES_DIST = dftables.c +@WITH_REBUILD_CHARTABLES_TRUE@am_dftables_OBJECTS = \ +@WITH_REBUILD_CHARTABLES_TRUE@ dftables.$(OBJEXT) +dftables_OBJECTS = $(am_dftables_OBJECTS) +dftables_LDADD = $(LDADD) +am__pcre_scanner_unittest_SOURCES_DIST = pcre_scanner_unittest.cc +@WITH_PCRE_CPP_TRUE@am_pcre_scanner_unittest_OBJECTS = \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner_unittest.$(OBJEXT) +pcre_scanner_unittest_OBJECTS = $(am_pcre_scanner_unittest_OBJECTS) +@WITH_PCRE_CPP_TRUE@pcre_scanner_unittest_DEPENDENCIES = \ +@WITH_PCRE_CPP_TRUE@ libpcrecpp.la +am__pcre_stringpiece_unittest_SOURCES_DIST = \ + pcre_stringpiece_unittest.cc +@WITH_PCRE_CPP_TRUE@am_pcre_stringpiece_unittest_OBJECTS = \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece_unittest.$(OBJEXT) +pcre_stringpiece_unittest_OBJECTS = \ + $(am_pcre_stringpiece_unittest_OBJECTS) +@WITH_PCRE_CPP_TRUE@pcre_stringpiece_unittest_DEPENDENCIES = \ +@WITH_PCRE_CPP_TRUE@ libpcrecpp.la +am__pcrecpp_unittest_SOURCES_DIST = pcrecpp_unittest.cc +@WITH_PCRE_CPP_TRUE@am_pcrecpp_unittest_OBJECTS = \ +@WITH_PCRE_CPP_TRUE@ pcrecpp_unittest.$(OBJEXT) +pcrecpp_unittest_OBJECTS = $(am_pcrecpp_unittest_OBJECTS) +@WITH_PCRE_CPP_TRUE@pcrecpp_unittest_DEPENDENCIES = libpcrecpp.la +am_pcregrep_OBJECTS = pcregrep.$(OBJEXT) +pcregrep_OBJECTS = $(am_pcregrep_OBJECTS) +am__DEPENDENCIES_1 = +pcregrep_DEPENDENCIES = libpcreposix.la $(am__DEPENDENCIES_1) \ + $(am__DEPENDENCIES_1) +am_pcretest_OBJECTS = pcretest.$(OBJEXT) +pcretest_OBJECTS = $(am_pcretest_OBJECTS) +pcretest_DEPENDENCIES = libpcreposix.la $(am__DEPENDENCIES_1) +binSCRIPT_INSTALL = $(INSTALL_SCRIPT) +SCRIPTS = $(bin_SCRIPTS) $(dist_noinst_SCRIPTS) +DEFAULT_INCLUDES = -I.@am__isrc@ +depcomp = $(SHELL) $(top_srcdir)/depcomp +am__depfiles_maybe = depfiles +COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ + $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +LTCOMPILE = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \ + $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +CCLD = $(CC) +LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) \ + $(LDFLAGS) -o $@ +CXXCOMPILE = $(CXX) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \ + $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CXXFLAGS) $(CXXFLAGS) +LTCXXCOMPILE = $(LIBTOOL) --tag=CXX $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=compile $(CXX) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \ + $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CXXFLAGS) $(CXXFLAGS) +CXXLD = $(CXX) +CXXLINK = $(LIBTOOL) --tag=CXX $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=link $(CXXLD) $(AM_CXXFLAGS) $(CXXFLAGS) $(AM_LDFLAGS) \ + $(LDFLAGS) -o $@ +SOURCES = $(libpcre_la_SOURCES) $(nodist_libpcre_la_SOURCES) \ + $(libpcrecpp_la_SOURCES) $(libpcreposix_la_SOURCES) \ + $(dftables_SOURCES) $(pcre_scanner_unittest_SOURCES) \ + $(pcre_stringpiece_unittest_SOURCES) \ + $(pcrecpp_unittest_SOURCES) $(pcregrep_SOURCES) \ + $(pcretest_SOURCES) +DIST_SOURCES = $(libpcre_la_SOURCES) $(am__libpcrecpp_la_SOURCES_DIST) \ + $(libpcreposix_la_SOURCES) $(am__dftables_SOURCES_DIST) \ + $(am__pcre_scanner_unittest_SOURCES_DIST) \ + $(am__pcre_stringpiece_unittest_SOURCES_DIST) \ + $(am__pcrecpp_unittest_SOURCES_DIST) $(pcregrep_SOURCES) \ + $(pcretest_SOURCES) +man1dir = $(mandir)/man1 +man3dir = $(mandir)/man3 +NROFF = nroff +MANS = $(dist_man_MANS) $(man_MANS) +dist_docDATA_INSTALL = $(INSTALL_DATA) +dist_htmlDATA_INSTALL = $(INSTALL_DATA) +htmlDATA_INSTALL = $(INSTALL_DATA) +pkgconfigDATA_INSTALL = $(INSTALL_DATA) +DATA = $(dist_doc_DATA) $(dist_html_DATA) $(dist_noinst_DATA) \ + $(html_DATA) $(pkgconfig_DATA) +am__include_HEADERS_DIST = pcreposix.h pcrecpp.h pcre_scanner.h +includeHEADERS_INSTALL = $(INSTALL_HEADER) +nodist_includeHEADERS_INSTALL = $(INSTALL_HEADER) +HEADERS = $(include_HEADERS) $(nodist_include_HEADERS) +ETAGS = etags +CTAGS = ctags +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +distdir = $(PACKAGE)-$(VERSION) +top_distdir = $(distdir) +am__remove_distdir = \ + { test ! -d $(distdir) \ + || { find $(distdir) -type d ! -perm -200 -exec chmod u+w {} ';' \ + && rm -fr $(distdir); }; } +DIST_ARCHIVES = $(distdir).tar.gz $(distdir).tar.bz2 $(distdir).zip +GZIP_ENV = --best +distuninstallcheck_listfiles = find . -type f -print +distcleancheck_listfiles = find . -type f -print +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AR = @AR@ +AS = @AS@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ CC = @CC@ -CXX = @CXX@ +CCDEPMODE = @CCDEPMODE@ CFLAGS = @CFLAGS@ +CPP = @CPP@ +CPPFLAGS = @CPPFLAGS@ +CXX = @CXX@ +CXXCPP = @CXXCPP@ +CXXDEPMODE = @CXXDEPMODE@ CXXFLAGS = @CXXFLAGS@ -LDFLAGS = @LDFLAGS@ -CXXLDFLAGS = @CXXLDFLAGS@ - -CC_FOR_BUILD = @CC_FOR_BUILD@ -CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@ -CXX_FOR_BUILD = @CXX_FOR_BUILD@ -CXXFLAGS_FOR_BUILD = @CXXFLAGS_FOR_BUILD@ -LDFLAGS_FOR_BUILD = $(LDFLAGS) - -UCP = @UCP@ -UTF8 = @UTF8@ -NEWLINE = @NEWLINE@ -POSIX_MALLOC_THRESHOLD = @POSIX_MALLOC_THRESHOLD@ -LINK_SIZE = @LINK_SIZE@ -MATCH_LIMIT = @MATCH_LIMIT@ @MATCH_LIMIT_RECURSION@ -NO_RECURSE = @NO_RECURSE@ -EBCDIC = @EBCDIC@ - +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +DISTCHECK_CONFIGURE_FLAGS = @DISTCHECK_CONFIGURE_FLAGS@ +DLLTOOL = @DLLTOOL@ +ECHO = @ECHO@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +EXEEXT = @EXEEXT@ +EXTRA_LIBPCRECPP_LDFLAGS = @EXTRA_LIBPCRECPP_LDFLAGS@ +EXTRA_LIBPCREPOSIX_LDFLAGS = @EXTRA_LIBPCREPOSIX_LDFLAGS@ +EXTRA_LIBPCRE_LDFLAGS = @EXTRA_LIBPCRE_LDFLAGS@ +F77 = @F77@ +FFLAGS = @FFLAGS@ +GREP = @GREP@ INSTALL = @INSTALL@ INSTALL_DATA = @INSTALL_DATA@ - -# LIBTOOL enables the building of shared and static libraries. It is set up -# to do one or the other or both by ./configure. - +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBBZ2 = @LIBBZ2@ +LIBOBJS = @LIBOBJS@ +LIBREADLINE = @LIBREADLINE@ +LIBS = @LIBS@ LIBTOOL = @LIBTOOL@ -LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) $(NO_RECURSE) $(EBCDIC) -LTCXXCOMPILE = $(LIBTOOL) --mode=compile $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) $(NO_RECURSE) $(EBCDIC) -@ON_WINDOWS@LINK = $(CC) $(LDFLAGS) -I. -I$(top_srcdir) -L.libs -@NOT_ON_WINDOWS@LINK = $(LIBTOOL) --mode=link $(CC) $(CFLAGS) $(LDFLAGS) -I. -I$(top_srcdir) -LINKLIB = $(LIBTOOL) --mode=link $(CC) -export-symbols-regex '^[^_]' $(LDFLAGS) -I. -I$(top_srcdir) -LINK_FOR_BUILD = $(LIBTOOL) --mode=link --tag=CC $(CC_FOR_BUILD) $(CFLAGS_FOR_BUILD) $(LDFLAGS_FOR_BUILD) -I. -I$(top_srcdir) -@ON_WINDOWS@CXXLINK = $(CXX) $(LDFLAGS) -I. -I$(top_srcdir) -L.libs -@NOT_ON_WINDOWS@CXXLINK = $(LIBTOOL) --mode=link $(CXX) $(CXXFLAGS) $(CXXLDFLAGS) -I. -I$(top_srcdir) -CXXLINKLIB = $(LIBTOOL) --mode=link $(CXX) $(LDFLAGS) -I. -I$(top_srcdir) - -# These are the version numbers for the shared libraries - -PCRELIBVERSION = @PCRE_LIB_VERSION@ -PCREPOSIXLIBVERSION = @PCRE_POSIXLIB_VERSION@ -PCRECPPLIBVERSION = @PCRE_CPPLIB_VERSION@ - -############################################################################## - - -OBJ = pcre_chartables.@OBJEXT@ \ - pcre_compile.@OBJEXT@ \ - pcre_config.@OBJEXT@ \ - pcre_dfa_exec.@OBJEXT@ \ - pcre_exec.@OBJEXT@ \ - pcre_fullinfo.@OBJEXT@ \ - pcre_get.@OBJEXT@ \ - pcre_globals.@OBJEXT@ \ - pcre_info.@OBJEXT@ \ - pcre_maketables.@OBJEXT@ \ - pcre_ord2utf8.@OBJEXT@ \ - pcre_refcount.@OBJEXT@ \ - pcre_study.@OBJEXT@ \ - pcre_tables.@OBJEXT@ \ - pcre_try_flipped.@OBJEXT@ \ - pcre_ucp_searchfuncs.@OBJEXT@ \ - pcre_valid_utf8.@OBJEXT@ \ - pcre_version.@OBJEXT@ \ - pcre_xclass.@OBJEXT@ \ - $(POSIX_OBJ) - -LOBJ = pcre_chartables.lo \ - pcre_compile.lo \ - pcre_config.lo \ - pcre_dfa_exec.lo \ - pcre_exec.lo \ - pcre_fullinfo.lo \ - pcre_get.lo \ - pcre_globals.lo \ - pcre_info.lo \ - pcre_maketables.lo \ - pcre_ord2utf8.lo \ - pcre_refcount.lo \ - pcre_study.lo \ - pcre_tables.lo \ - pcre_try_flipped.lo \ - pcre_ucp_searchfuncs.lo \ - pcre_valid_utf8.lo \ - pcre_version.lo \ - pcre_xclass.lo \ - $(POSIX_LOBJ) - -CPPOBJ = pcrecpp.@OBJEXT@ \ - pcre_scanner.@OBJEXT@ \ - pcre_stringpiece.@OBJEXT@ - -CPPLOBJ = pcrecpp.lo \ - pcre_scanner.lo \ - pcre_stringpiece.lo - -CPP_TARGETS = libpcrecpp.la \ - pcrecpp_unittest@EXEEXT@ \ - pcre_scanner_unittest@EXEEXT@ \ - pcre_stringpiece_unittest@EXEEXT@ - -all: libpcre.la @POSIX_LIB@ pcretest@EXEEXT@ pcregrep@EXEEXT@ \ - @MAYBE_CPP_TARGETS@ @ON_WINDOWS@ winshared - -pcregrep@EXEEXT@: libpcre.la pcregrep.@OBJEXT@ @ON_WINDOWS@ winshared - $(LINK) -o pcregrep@EXEEXT@ pcregrep.@OBJEXT@ libpcre.la - -pcretest@EXEEXT@: libpcre.la @POSIX_LIB@ pcretest.@OBJEXT@ \ - @ON_WINDOWS@ winshared - $(LINK) $(PURIFY) $(EFENCE) -o pcretest@EXEEXT@ \ - pcretest.@OBJEXT@ \ - libpcre.la @POSIX_LIB@ - -pcrecpp_unittest@EXEEXT@: libpcrecpp.la pcrecpp_unittest.@OBJEXT@ \ - @ON_WINDOWS@ winshared - $(CXXLINK) $(PURIFY) $(EFENCE) -o pcrecpp_unittest@EXEEXT@ \ - pcrecpp_unittest.@OBJEXT@ \ - libpcrecpp.la @POSIX_LIB@ - -pcre_scanner_unittest@EXEEXT@: libpcrecpp.la pcre_scanner_unittest.@OBJEXT@ \ - @ON_WINDOWS@ winshared - $(CXXLINK) $(PURIFY) $(EFENCE) \ - -o pcre_scanner_unittest@EXEEXT@ \ - pcre_scanner_unittest.@OBJEXT@ \ - libpcrecpp.la @POSIX_LIB@ - -pcre_stringpiece_unittest@EXEEXT@: libpcrecpp.la \ - pcre_stringpiece_unittest.@OBJEXT@ @ON_WINDOWS@ winshared - $(CXXLINK) $(PURIFY) $(EFENCE) \ - -o pcre_stringpiece_unittest@EXEEXT@ \ - pcre_stringpiece_unittest.@OBJEXT@ \ - libpcrecpp.la @POSIX_LIB@ - -libpcre.la: $(OBJ) - -rm -f libpcre.la - $(LINKLIB) -rpath $(LIBDIR) -version-info \ - '$(PCRELIBVERSION)' -o libpcre.la $(LOBJ) - -libpcreposix.la: libpcre.la pcreposix.@OBJEXT@ - -rm -f libpcreposix.la - $(LINKLIB) -rpath $(LIBDIR) libpcre.la -version-info \ - '$(PCREPOSIXLIBVERSION)' -o libpcreposix.la pcreposix.lo - -libpcrecpp.la: libpcre.la $(CPPOBJ) - -rm -f libpcrecpp.la - $(CXXLINKLIB) -rpath $(LIBDIR) libpcre.la -version-info \ - '$(PCRECPPLIBVERSION)' -o libpcrecpp.la $(CPPLOBJ) - -# Note that files generated by ./configure and by dftables are in the current -# directory, not the source directory. - -pcre_chartables.@OBJEXT@: pcre_chartables.c - @$(LTCOMPILE) pcre_chartables.c - -pcre_compile.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_compile.c \ - $(top_srcdir)/pcre_printint.src - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_compile.c - -pcre_config.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_config.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_config.c - -pcre_dfa_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_dfa_exec.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_dfa_exec.c - -pcre_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_exec.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_exec.c - -pcre_fullinfo.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_fullinfo.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_fullinfo.c - -pcre_get.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_get.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_get.c - -pcre_globals.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_globals.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_globals.c - -pcre_info.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_info.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_info.c - -pcre_maketables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_maketables.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_maketables.c - -pcre_ord2utf8.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_ord2utf8.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_ord2utf8.c - -pcre_refcount.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_refcount.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_refcount.c - -pcre_study.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_study.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_study.c - -pcre_tables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_tables.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_tables.c - -pcre_try_flipped.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_try_flipped.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_try_flipped.c - -pcre_ucp_searchfuncs.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h \ - $(top_srcdir)/pcre_ucp_searchfuncs.c \ - $(top_srcdir)/ucptable.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_ucp_searchfuncs.c - -pcre_valid_utf8.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_valid_utf8.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_valid_utf8.c - -pcre_version.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_version.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_version.c - -pcre_xclass.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_xclass.c - @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_xclass.c - -pcreposix.@OBJEXT@: $(top_srcdir)/pcreposix.c $(top_srcdir)/pcreposix.h \ - $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre.h config.h Makefile - @$(LTCOMPILE) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcreposix.c - -pcrecpp.@OBJEXT@: $(top_srcdir)/pcrecpp.cc $(top_srcdir)/pcrecpp.h \ - pcrecpparg.h pcre_stringpiece.h $(top_srcdir)/pcre.h config.h Makefile - @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcrecpp.cc - -pcre_scanner.@OBJEXT@: $(top_srcdir)/pcre_scanner.cc \ - $(top_srcdir)/pcre_scanner.h \ - $(top_srcdir)/pcrecpp.h pcrecpparg.h pcre_stringpiece.h \ - $(top_srcdir)/pcre.h config.h Makefile - @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_scanner.cc - -pcre_stringpiece.@OBJEXT@: $(top_srcdir)/pcre_stringpiece.cc \ - pcre_stringpiece.h \ - config.h Makefile - @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ - $(top_srcdir)/pcre_stringpiece.cc - -pcretest.@OBJEXT@: $(top_srcdir)/pcretest.c $(top_srcdir)/pcre_internal.h \ - $(top_srcdir)/pcre_printint.src $(top_srcdir)/pcre.h config.h Makefile - $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ - $(LINK_SIZE) $(top_srcdir)/pcretest.c - -pcrecpp_unittest.@OBJEXT@: $(top_srcdir)/pcrecpp_unittest.cc \ - $(top_srcdir)/pcrecpp.h \ - pcrecpparg.h pcre_stringpiece.h $(top_srcdir)/pcre.h config.h Makefile - $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ - $(LINK_SIZE) $(top_srcdir)/pcrecpp_unittest.cc - -pcre_stringpiece_unittest.@OBJEXT@: $(top_srcdir)/pcre_stringpiece_unittest.cc \ - pcre_stringpiece.h pcrecpparg.h config.h Makefile - $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ - $(LINK_SIZE) $(top_srcdir)/pcre_stringpiece_unittest.cc - -pcre_scanner_unittest.@OBJEXT@: $(top_srcdir)/pcre_scanner_unittest.cc \ - $(top_srcdir)/pcre_scanner.h \ - $(top_srcdir)/pcrecpp.h pcre_stringpiece.h \ - $(top_srcdir)/pcre.h pcrecpparg.h config.h Makefile - $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ - $(LINK_SIZE) $(top_srcdir)/pcre_scanner_unittest.cc - -pcregrep.@OBJEXT@: $(top_srcdir)/pcregrep.c $(top_srcdir)/pcre.h Makefile config.h - $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ - $(PCREGREP_OSTYPE) $(top_srcdir)/pcregrep.c - -# Some Windows-specific targets for MinGW. Do not use for Cygwin. - -winshared : .libs/@WIN_PREFIX@pcre.dll .libs/@WIN_PREFIX@pcreposix.dll \ - .libs/@WIN_PREFIX@pcrecpp.dll - -.libs/@WIN_PREFIX@pcre.dll : libpcre.la - $(CC) $(CFLAGS) -shared -o $@ \ - -Wl,--whole-archive .libs/libpcre.a \ - -Wl,--out-implib,.libs/libpcre.dll.a \ - -Wl,--output-def,.libs/@WIN_PREFIX@pcre.dll-def \ - -Wl,--export-all-symbols \ - -Wl,--no-whole-archive - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ - -e "s#library_names=''#library_names='libpcre.dll.a'#" \ - < .libs/libpcre.lai > .libs/libpcre.lai.tmp && \ - mv -f .libs/libpcre.lai.tmp .libs/libpcre.lai - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ - -e "s#library_names=''#library_names='libpcre.dll.a'#" \ - < libpcre.la > libpcre.la.tmp && \ - mv -f libpcre.la.tmp libpcre.la - - -.libs/@WIN_PREFIX@pcreposix.dll: libpcreposix.la libpcre.la - $(CC) $(CFLAGS) -shared -o $@ \ - -Wl,--whole-archive .libs/libpcreposix.a \ - -Wl,--out-implib,.libs/@WIN_PREFIX@pcreposix.dll.a \ - -Wl,--output-def,.libs/@WIN_PREFIX@libpcreposix.dll-def \ - -Wl,--export-all-symbols \ - -Wl,--no-whole-archive .libs/libpcre.a - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ - -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ - < .libs/libpcreposix.lai > .libs/libpcreposix.lai.tmp && \ - mv -f .libs/libpcreposix.lai.tmp .libs/libpcreposix.lai - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ - -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ - < libpcreposix.la > libpcreposix.la.tmp && \ - mv -f libpcreposix.la.tmp libpcreposix.la - -.libs/@WIN_PREFIX@pcrecpp.dll: libpcrecpp.la libpcre.la - $(CXX) $(CXXFLAGS) -shared -o $@ \ - -Wl,--whole-archive .libs/libpcrecpp.a \ - -Wl,--out-implib,.libs/@WIN_PREFIX@pcrecpp.dll.a \ - -Wl,--output-def,.libs/@WIN_PREFIX@libpcrecpp.dll-def \ - -Wl,--export-all-symbols \ - -Wl,--no-whole-archive .libs/libpcre.a - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcrecpp.dll'#" \ - -e "s#library_names=''#library_names='libpcrecpp.dll.a'#"\ - < .libs/libpcrecpp.lai > .libs/libpcrecpp.lai.tmp && \ - mv -f .libs/libpcrecpp.lai.tmp .libs/libpcrecpp.lai - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcrecpp.dll'#" \ - -e "s#library_names=''#library_names='libpcrecpp.dll.a'#"\ - < libpcrecpp.la > libpcrecpp.la.tmp && \ - mv -f libpcrecpp.la.tmp libpcrecpp.la - - -wininstall : winshared - $(mkinstalldirs) $(DESTDIR)$(LIBDIR) - $(mkinstalldirs) $(DESTDIR)$(BINDIR) - $(INSTALL) .libs/@WIN_PREFIX@pcre.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll - $(INSTALL) .libs/@WIN_PREFIX@pcreposix.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll - $(INSTALL) .libs/@WIN_PREFIX@libpcreposix.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcreposix.dll.a - $(INSTALL) .libs/@WIN_PREFIX@libpcre.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcre.dll.a -@HAVE_CPP@ $(INSTALL) .libs/@WIN_PREFIX@pcrecpp.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcrecpp.dll -@HAVE_CPP@ $(INSTALL) .libs/@WIN_PREFIX@libpcrecpp.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcrecpp.dll.a - -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll - -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll -@HAVE_CPP@ -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcrecpp.dll - -strip $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ - -strip $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ - -# An auxiliary program makes the default character table source. This is put -# in the current directory, NOT the $top_srcdir directory. - -pcre_chartables.c: dftables@BUILD_EXEEXT@ - ./dftables@BUILD_EXEEXT@ pcre_chartables.c - -dftables.@BUILD_OBJEXT@: $(top_srcdir)/dftables.c \ - $(top_srcdir)/pcre_maketables.c $(top_srcdir)/pcre_internal.h \ - $(top_srcdir)/pcre.h config.h Makefile - $(CC_FOR_BUILD) -c $(CFLAGS_FOR_BUILD) -I. $(top_srcdir)/dftables.c - -dftables@BUILD_EXEEXT@: dftables.@BUILD_OBJEXT@ - $(LINK_FOR_BUILD) -o dftables@BUILD_EXEEXT@ dftables.@OBJEXT@ - -install: all @ON_WINDOWS@ wininstall -@NOT_ON_WINDOWS@ $(mkinstalldirs) $(DESTDIR)$(LIBDIR) -@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la" -@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la -@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la" -@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la -@NOT_ON_WINDOWS@@HAVE_CPP@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcrecpp.la $(DESTDIR)$(LIBDIR)/libpcrecpp.la" -@NOT_ON_WINDOWS@@HAVE_CPP@ $(LIBTOOL) --mode=install $(INSTALL) libpcrecpp.la $(DESTDIR)$(LIBDIR)/libpcrecpp.la -@NOT_ON_WINDOWS@ $(LIBTOOL) --finish $(DESTDIR)$(LIBDIR) - $(mkinstalldirs) $(DESTDIR)$(INCDIR) - $(INSTALL_DATA) $(top_srcdir)/pcre.h $(DESTDIR)$(INCDIR)/pcre.h - $(INSTALL_DATA) $(top_srcdir)/pcreposix.h $(DESTDIR)$(INCDIR)/pcreposix.h -@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/pcrecpp.h $(DESTDIR)$(INCDIR)/pcrecpp.h -@HAVE_CPP@ $(INSTALL_DATA) pcrecpparg.h $(DESTDIR)$(INCDIR)/pcrecpparg.h -@HAVE_CPP@ $(INSTALL_DATA) pcre_stringpiece.h $(DESTDIR)$(INCDIR)/pcre_stringpiece.h -@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/pcre_scanner.h $(DESTDIR)$(INCDIR)/pcre_scanner.h - $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre.3 $(DESTDIR)$(MANDIR)/man3/pcre.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreapi.3 $(DESTDIR)$(MANDIR)/man3/pcreapi.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrebuild.3 $(DESTDIR)$(MANDIR)/man3/pcrebuild.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrecallout.3 $(DESTDIR)$(MANDIR)/man3/pcrecallout.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrecompat.3 $(DESTDIR)$(MANDIR)/man3/pcrecompat.3 -@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/doc/pcrecpp.3 $(DESTDIR)$(MANDIR)/man3/pcrecpp.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrematching.3 $(DESTDIR)$(MANDIR)/man3/pcrematching.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrepartial.3 $(DESTDIR)$(MANDIR)/man3/pcrepartial.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrepattern.3 $(DESTDIR)$(MANDIR)/man3/pcrepattern.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreperform.3 $(DESTDIR)$(MANDIR)/man3/pcreperform.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreposix.3 $(DESTDIR)$(MANDIR)/man3/pcreposix.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreprecompile.3 $(DESTDIR)$(MANDIR)/man3/pcreprecompile.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcresample.3 $(DESTDIR)$(MANDIR)/man3/pcresample.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrestack.3 $(DESTDIR)$(MANDIR)/man3/pcrestack.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_compile.3 $(DESTDIR)$(MANDIR)/man3/pcre_compile.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_compile2.3 $(DESTDIR)$(MANDIR)/man3/pcre_compile2.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_config.3 $(DESTDIR)$(MANDIR)/man3/pcre_config.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_named_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_dfa_exec.3 $(DESTDIR)$(MANDIR)/man3/pcre_dfa_exec.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_exec.3 $(DESTDIR)$(MANDIR)/man3/pcre_exec.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring_list.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_fullinfo.3 $(DESTDIR)$(MANDIR)/man3/pcre_fullinfo.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_named_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_stringnumber.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_stringnumber.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_stringtable_entries.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_stringtable_entries.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring_list.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_info.3 $(DESTDIR)$(MANDIR)/man3/pcre_info.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_maketables.3 $(DESTDIR)$(MANDIR)/man3/pcre_maketables.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_refcount.3 $(DESTDIR)$(MANDIR)/man3/pcre_refcount.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_study.3 $(DESTDIR)$(MANDIR)/man3/pcre_study.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_version.3 $(DESTDIR)$(MANDIR)/man3/pcre_version.3 - $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man1 - $(INSTALL_DATA) $(top_srcdir)/doc/pcregrep.1 $(DESTDIR)$(MANDIR)/man1/pcregrep.1 - $(INSTALL_DATA) $(top_srcdir)/doc/pcretest.1 $(DESTDIR)$(MANDIR)/man1/pcretest.1 - $(mkinstalldirs) $(DESTDIR)$(BINDIR) - $(LIBTOOL) --mode=install $(INSTALL) pcregrep@EXEEXT@ $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ - $(LIBTOOL) --mode=install $(INSTALL) pcretest@EXEEXT@ $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ - $(INSTALL) pcre-config $(DESTDIR)$(BINDIR)/pcre-config - $(mkinstalldirs) $(DESTDIR)$(LIBDIR)/pkgconfig - $(INSTALL_DATA) libpcre.pc $(DESTDIR)$(LIBDIR)/pkgconfig/libpcre.pc - -# The uninstall target removes all the files that were installed. - -uninstall:; -rm -rf \ - $(DESTDIR)$(LIBDIR)/libpcre.* \ - $(DESTDIR)$(LIBDIR)/libpcreposix.* \ - $(DESTDIR)$(LIBDIR)/libpcrecpp.* \ - $(DESTDIR)$(INCDIR)/pcre.h \ - $(DESTDIR)$(INCDIR)/pcreposix.h \ - $(DESTDIR)$(INCDIR)/pcrecpp.h \ - $(DESTDIR)$(INCDIR)/pcrecpparg.h \ - $(DESTDIR)$(INCDIR)/pcre_scanner.h \ - $(DESTDIR)$(INCDIR)/pcre_stringpiece.h \ - $(DESTDIR)$(MANDIR)/man3/pcre.3 \ - $(DESTDIR)$(MANDIR)/man3/pcreapi.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrebuild.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrecallout.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrecompat.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrecpp.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrematching.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrepartial.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrepattern.3 \ - $(DESTDIR)$(MANDIR)/man3/pcreperform.3 \ - $(DESTDIR)$(MANDIR)/man3/pcreposix.3 \ - $(DESTDIR)$(MANDIR)/man3/pcreprecompile.3 \ - $(DESTDIR)$(MANDIR)/man3/pcresample.3 \ - $(DESTDIR)$(MANDIR)/man3/pcrestack.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_compile.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_compile2.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_config.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_copy_named_substring.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_copy_substring.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_dfa_exec.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_exec.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_free_substring.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_free_substring_list.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_fullinfo.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_get_named_substring.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_get_stringnumber.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_get_stringtable_entries.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_get_substring.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_get_substring_list.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_info.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_maketables.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_refcount.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_study.3 \ - $(DESTDIR)$(MANDIR)/man3/pcre_version.3 \ - $(DESTDIR)$(MANDIR)/man1/pcregrep.1 \ - $(DESTDIR)$(MANDIR)/man1/pcretest.1 \ - $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ \ - $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ \ - $(DESTDIR)$(BINDIR)/pcre-config \ - $(DESTDIR)$(LIBDIR)/pkgconfig/libpcre.pc - -# We deliberately omit dftables and pcre_chartables.c from 'make clean'; once -# made pcre_chartables.c shouldn't change, and if people have edited the tables -# by hand, you don't want to throw them away. - -clean:; -rm -rf *.@OBJEXT@ *.lo *.a *.la .libs pcretest@EXEEXT@ pcre_stringpiece_unittest@EXEEXT@ pcrecpp_unittest@EXEEXT@ pcre_scanner_unittest@EXEEXT@ pcregrep@EXEEXT@ testtry - -# But "make distclean" should get back to a virgin distribution - -distclean: clean - -rm -f pcre_chartables.c libtool pcre-config libpcre.pc \ - pcre_stringpiece.h pcrecpparg.h \ - dftables@EXEEXT@ RunGrepTest RunTest \ - Makefile config.h config.status config.log config.cache - -check: runtest - -@WIN_PREFIX@pcre.dll : winshared - cp .libs/@WIN_PREFIX@pcre.dll . - -test: runtest - -runtest: all @ON_WINDOWS@ @WIN_PREFIX@pcre.dll - @./RunTest - @./RunGrepTest -@HAVE_CPP@ @echo "" -@HAVE_CPP@ @echo "Testing C++ wrapper" -@HAVE_CPP@ @echo ""; echo "Test 1++: stringpiece" -@HAVE_CPP@ @./pcre_stringpiece_unittest@EXEEXT@ -@HAVE_CPP@ @echo ""; echo "Test 2++: RE class" -@HAVE_CPP@ @./pcrecpp_unittest@EXEEXT@ -@HAVE_CPP@ @echo ""; echo "Test 3++: Scanner class" -@HAVE_CPP@ @./pcre_scanner_unittest@EXEEXT@ - -# End +LIBZ = @LIBZ@ +LN_S = @LN_S@ +LTLIBOBJS = @LTLIBOBJS@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +OBJDUMP = @OBJDUMP@ +OBJEXT = @OBJEXT@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PCRE_DATE = @PCRE_DATE@ +PCRE_MAJOR = @PCRE_MAJOR@ +PCRE_MINOR = @PCRE_MINOR@ +PCRE_PRERELEASE = @PCRE_PRERELEASE@ +RANLIB = @RANLIB@ +SED = @SED@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +VERSION = @VERSION@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +ac_ct_CXX = @ac_ct_CXX@ +ac_ct_F77 = @ac_ct_F77@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_vendor = @build_vendor@ +builddir = @builddir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +localedir = @localedir@ +localstatedir = @localstatedir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pcre_have_bits_type_traits = @pcre_have_bits_type_traits@ +pcre_have_long_long = @pcre_have_long_long@ +pcre_have_type_traits = @pcre_have_type_traits@ +pcre_have_ulong_long = @pcre_have_ulong_long@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +dist_doc_DATA = \ + doc/pcre.txt \ + doc/pcre-config.txt \ + doc/pcregrep.txt \ + doc/pcretest.txt \ + AUTHORS \ + COPYING \ + ChangeLog \ + LICENCE \ + NEWS \ + README + +dist_html_DATA = \ + doc/html/index.html \ + doc/html/pcre.html \ + doc/html/pcre-config.html \ + doc/html/pcre_compile.html \ + doc/html/pcre_compile2.html \ + doc/html/pcre_config.html \ + doc/html/pcre_copy_named_substring.html \ + doc/html/pcre_copy_substring.html \ + doc/html/pcre_dfa_exec.html \ + doc/html/pcre_exec.html \ + doc/html/pcre_free_substring.html \ + doc/html/pcre_free_substring_list.html \ + doc/html/pcre_fullinfo.html \ + doc/html/pcre_get_named_substring.html \ + doc/html/pcre_get_stringnumber.html \ + doc/html/pcre_get_stringtable_entries.html \ + doc/html/pcre_get_substring.html \ + doc/html/pcre_get_substring_list.html \ + doc/html/pcre_info.html \ + doc/html/pcre_maketables.html \ + doc/html/pcre_refcount.html \ + doc/html/pcre_study.html \ + doc/html/pcre_version.html \ + doc/html/pcreapi.html \ + doc/html/pcrebuild.html \ + doc/html/pcrecallout.html \ + doc/html/pcrecompat.html \ + doc/html/pcregrep.html \ + doc/html/pcrematching.html \ + doc/html/pcrepartial.html \ + doc/html/pcrepattern.html \ + doc/html/pcreperform.html \ + doc/html/pcreposix.html \ + doc/html/pcreprecompile.html \ + doc/html/pcresample.html \ + doc/html/pcrestack.html \ + doc/html/pcresyntax.html \ + doc/html/pcretest.html + +pcrecpp_html = doc/html/pcrecpp.html +dist_noinst_DATA = $(pcrecpp_html) +@WITH_PCRE_CPP_TRUE@html_DATA = $(pcrecpp_html) + +# The Libtool libraries to install. We'll add to this later. +lib_LTLIBRARIES = libpcre.la libpcreposix.la $(am__append_4) +check_SCRIPTS = +dist_noinst_SCRIPTS = RunTest RunGrepTest + +# Additional files to delete on 'make clean' and 'make maintainer-clean'. +CLEANFILES = pcre_chartables.c testsavedregex teststderr testtry \ + testNinput +MAINTAINERCLEANFILES = pcre.h.generic + +# Additional files to bundle with the distribution, over and above what +# the Autotools include by default. + +# These files contain maintenance information + +# These files are used in the preparation of a release + +# These files are to do with building for Virtual Pascal + +# These files are usable versions of pcre.h and config.h that are distributed +# for the benefit of people who are building PCRE manually, without the +# Autotools support. + +# The pcre_printint.src file is #included by some source files, so it must be +# distributed. The pcre_chartables.c.dist file is the default version of +# pcre_chartables.c, used unless --enable-rebuild-chartables is specified. + +# PCRE demonstration program. No longer built automatcally. The point is that +# the users should build it themselves. So just distribute the source. +# noinst_PROGRAMS += pcredemo +# pcredemo_SOURCES = pcredemo.c +# pcredemo_LDADD = libpcre.la +EXTRA_DIST = doc/perltest.txt NON-UNIX-USE HACKING PrepareRelease \ + CleanTxt Detrail 132html doc/index.html.src makevp.bat \ + makevp_c.txt makevp_l.txt pcregexp.pas pcre.h.generic \ + config.h.generic pcre_printint.src pcre_chartables.c.dist \ + RunTest.bat testdata/grepinput testdata/grepinput8 \ + testdata/grepinputv testdata/grepinputx testdata/greplist \ + testdata/grepoutput testdata/grepoutput8 testdata/grepoutputN \ + testdata/testinput1 testdata/testinput2 testdata/testinput3 \ + testdata/testinput4 testdata/testinput5 testdata/testinput6 \ + testdata/testinput7 testdata/testinput8 testdata/testinput9 \ + testdata/testinput10 testdata/testoutput1 testdata/testoutput2 \ + testdata/testoutput3 testdata/testoutput4 testdata/testoutput5 \ + testdata/testoutput6 testdata/testoutput7 testdata/testoutput8 \ + testdata/testoutput9 testdata/testoutput10 \ + testdata/wintestinput3 testdata/wintestoutput3 perltest.pl \ + pcredemo.c $(pcrecpp_man) cmake/COPYING-CMAKE-SCRIPTS \ + cmake/FindPackageHandleStandardArgs.cmake \ + cmake/FindReadline.cmake CMakeLists.txt config-cmake.h.in + +# These are the header files we'll install. We do not distribute pcre.h because +# it is generated from pcre.h.in. +nodist_include_HEADERS = pcre.h $(am__append_1) +include_HEADERS = pcreposix.h $(am__append_2) +bin_SCRIPTS = pcre-config +@WITH_REBUILD_CHARTABLES_TRUE@dftables_SOURCES = dftables.c +libpcre_la_SOURCES = \ + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_internal.h \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucd.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + ucp.h + +nodist_libpcre_la_SOURCES = \ + pcre_chartables.c + +libpcre_la_LDFLAGS = $(EXTRA_LIBPCRE_LDFLAGS) +libpcreposix_la_SOURCES = \ + pcreposix.c + +libpcreposix_la_LDFLAGS = $(EXTRA_LIBPCREPOSIX_LDFLAGS) +libpcreposix_la_LIBADD = libpcre.la +@WITH_PCRE_CPP_TRUE@libpcrecpp_la_SOURCES = \ +@WITH_PCRE_CPP_TRUE@ pcrecpp_internal.h \ +@WITH_PCRE_CPP_TRUE@ pcrecpp.cc \ +@WITH_PCRE_CPP_TRUE@ pcre_scanner.cc \ +@WITH_PCRE_CPP_TRUE@ pcre_stringpiece.cc + +@WITH_PCRE_CPP_TRUE@libpcrecpp_la_LDFLAGS = $(EXTRA_LIBPCRECPP_LDFLAGS) +@WITH_PCRE_CPP_TRUE@libpcrecpp_la_LIBADD = libpcre.la +@WITH_PCRE_CPP_TRUE@pcrecpp_unittest_SOURCES = pcrecpp_unittest.cc +@WITH_PCRE_CPP_TRUE@pcrecpp_unittest_LDADD = libpcrecpp.la +@WITH_PCRE_CPP_TRUE@pcre_scanner_unittest_SOURCES = pcre_scanner_unittest.cc +@WITH_PCRE_CPP_TRUE@pcre_scanner_unittest_LDADD = libpcrecpp.la +@WITH_PCRE_CPP_TRUE@pcre_stringpiece_unittest_SOURCES = pcre_stringpiece_unittest.cc +@WITH_PCRE_CPP_TRUE@pcre_stringpiece_unittest_LDADD = libpcrecpp.la +pcretest_SOURCES = pcretest.c +pcretest_LDADD = libpcreposix.la $(LIBREADLINE) +pcregrep_SOURCES = pcregrep.c +pcregrep_LDADD = libpcreposix.la $(LIBZ) $(LIBBZ2) + +# A PCRE user submitted the following addition, saying that it "will allow +# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a +# nice DLL for Windows use". (It is used by the pcre.dll target.) +DLL_OBJS = pcre_compile.o pcre_config.o \ + pcre_dfa_exec.o pcre_exec.o pcre_fullinfo.o pcre_get.o \ + pcre_globals.o pcre_info.o pcre_maketables.o \ + pcre_newline.o pcre_ord2utf8.o pcre_refcount.o \ + pcre_study.o pcre_tables.o pcre_try_flipped.o \ + pcre_ucd.o pcre_valid_utf8.o pcre_version.o \ + pcre_chartables.o \ + pcre_xclass.o + + +# We have .pc files for pkg-config users. +pkgconfigdir = $(libdir)/pkgconfig +pkgconfig_DATA = libpcre.pc $(am__append_7) +dist_man_MANS = \ + doc/pcre.3 \ + doc/pcre-config.1 \ + doc/pcre_compile.3 \ + doc/pcre_compile2.3 \ + doc/pcre_config.3 \ + doc/pcre_copy_named_substring.3 \ + doc/pcre_copy_substring.3 \ + doc/pcre_dfa_exec.3 \ + doc/pcre_exec.3 \ + doc/pcre_free_substring.3 \ + doc/pcre_free_substring_list.3 \ + doc/pcre_fullinfo.3 \ + doc/pcre_get_named_substring.3 \ + doc/pcre_get_stringnumber.3 \ + doc/pcre_get_stringtable_entries.3 \ + doc/pcre_get_substring.3 \ + doc/pcre_get_substring_list.3 \ + doc/pcre_info.3 \ + doc/pcre_maketables.3 \ + doc/pcre_refcount.3 \ + doc/pcre_study.3 \ + doc/pcre_version.3 \ + doc/pcreapi.3 \ + doc/pcrebuild.3 \ + doc/pcrecallout.3 \ + doc/pcrecompat.3 \ + doc/pcregrep.1 \ + doc/pcrematching.3 \ + doc/pcrepartial.3 \ + doc/pcrepattern.3 \ + doc/pcreperform.3 \ + doc/pcreposix.3 \ + doc/pcreprecompile.3 \ + doc/pcresample.3 \ + doc/pcrestack.3 \ + doc/pcresyntax.3 \ + doc/pcretest.1 + +pcrecpp_man = doc/pcrecpp.3 +@WITH_PCRE_CPP_TRUE@man_MANS = $(pcrecpp_man) +all: config.h + $(MAKE) $(AM_MAKEFLAGS) all-am + +.SUFFIXES: +.SUFFIXES: .c .cc .lo .o .obj +am--refresh: + @: +$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + echo ' cd $(srcdir) && $(AUTOMAKE) --gnu '; \ + cd $(srcdir) && $(AUTOMAKE) --gnu \ + && exit 0; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu Makefile'; \ + cd $(top_srcdir) && \ + $(AUTOMAKE) --gnu Makefile +.PRECIOUS: Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + echo ' $(SHELL) ./config.status'; \ + $(SHELL) ./config.status;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $@ $(am__depfiles_maybe);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + $(SHELL) ./config.status --recheck + +$(top_srcdir)/configure: $(am__configure_deps) + cd $(srcdir) && $(AUTOCONF) +$(ACLOCAL_M4): $(am__aclocal_m4_deps) + cd $(srcdir) && $(ACLOCAL) $(ACLOCAL_AMFLAGS) + +config.h: stamp-h1 + @if test ! -f $@; then \ + rm -f stamp-h1; \ + $(MAKE) $(AM_MAKEFLAGS) stamp-h1; \ + else :; fi + +stamp-h1: $(srcdir)/config.h.in $(top_builddir)/config.status + @rm -f stamp-h1 + cd $(top_builddir) && $(SHELL) ./config.status config.h +$(srcdir)/config.h.in: $(am__configure_deps) + cd $(top_srcdir) && $(AUTOHEADER) + rm -f stamp-h1 + touch $@ + +distclean-hdr: + -rm -f config.h stamp-h1 +libpcre.pc: $(top_builddir)/config.status $(srcdir)/libpcre.pc.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +libpcrecpp.pc: $(top_builddir)/config.status $(srcdir)/libpcrecpp.pc.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +pcre-config: $(top_builddir)/config.status $(srcdir)/pcre-config.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +pcre.h: $(top_builddir)/config.status $(srcdir)/pcre.h.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +pcre_stringpiece.h: $(top_builddir)/config.status $(srcdir)/pcre_stringpiece.h.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +pcrecpparg.h: $(top_builddir)/config.status $(srcdir)/pcrecpparg.h.in + cd $(top_builddir) && $(SHELL) ./config.status $@ +install-libLTLIBRARIES: $(lib_LTLIBRARIES) + @$(NORMAL_INSTALL) + test -z "$(libdir)" || $(MKDIR_P) "$(DESTDIR)$(libdir)" + @list='$(lib_LTLIBRARIES)'; for p in $$list; do \ + if test -f $$p; then \ + f=$(am__strip_dir) \ + echo " $(LIBTOOL) --mode=install $(libLTLIBRARIES_INSTALL) $(INSTALL_STRIP_FLAG) '$$p' '$(DESTDIR)$(libdir)/$$f'"; \ + $(LIBTOOL) --mode=install $(libLTLIBRARIES_INSTALL) $(INSTALL_STRIP_FLAG) "$$p" "$(DESTDIR)$(libdir)/$$f"; \ + else :; fi; \ + done + +uninstall-libLTLIBRARIES: + @$(NORMAL_UNINSTALL) + @list='$(lib_LTLIBRARIES)'; for p in $$list; do \ + p=$(am__strip_dir) \ + echo " $(LIBTOOL) --mode=uninstall rm -f '$(DESTDIR)$(libdir)/$$p'"; \ + $(LIBTOOL) --mode=uninstall rm -f "$(DESTDIR)$(libdir)/$$p"; \ + done + +clean-libLTLIBRARIES: + -test -z "$(lib_LTLIBRARIES)" || rm -f $(lib_LTLIBRARIES) + @list='$(lib_LTLIBRARIES)'; for p in $$list; do \ + dir="`echo $$p | sed -e 's|/[^/]*$$||'`"; \ + test "$$dir" != "$$p" || dir=.; \ + echo "rm -f \"$${dir}/so_locations\""; \ + rm -f "$${dir}/so_locations"; \ + done +libpcre.la: $(libpcre_la_OBJECTS) $(libpcre_la_DEPENDENCIES) + $(libpcre_la_LINK) -rpath $(libdir) $(libpcre_la_OBJECTS) $(libpcre_la_LIBADD) $(LIBS) +libpcrecpp.la: $(libpcrecpp_la_OBJECTS) $(libpcrecpp_la_DEPENDENCIES) + $(libpcrecpp_la_LINK) $(am_libpcrecpp_la_rpath) $(libpcrecpp_la_OBJECTS) $(libpcrecpp_la_LIBADD) $(LIBS) +libpcreposix.la: $(libpcreposix_la_OBJECTS) $(libpcreposix_la_DEPENDENCIES) + $(libpcreposix_la_LINK) -rpath $(libdir) $(libpcreposix_la_OBJECTS) $(libpcreposix_la_LIBADD) $(LIBS) +install-binPROGRAMS: $(bin_PROGRAMS) + @$(NORMAL_INSTALL) + test -z "$(bindir)" || $(MKDIR_P) "$(DESTDIR)$(bindir)" + @list='$(bin_PROGRAMS)'; for p in $$list; do \ + p1=`echo $$p|sed 's/$(EXEEXT)$$//'`; \ + if test -f $$p \ + || test -f $$p1 \ + ; then \ + f=`echo "$$p1" | sed 's,^.*/,,;$(transform);s/$$/$(EXEEXT)/'`; \ + echo " $(INSTALL_PROGRAM_ENV) $(LIBTOOL) --mode=install $(binPROGRAMS_INSTALL) '$$p' '$(DESTDIR)$(bindir)/$$f'"; \ + $(INSTALL_PROGRAM_ENV) $(LIBTOOL) --mode=install $(binPROGRAMS_INSTALL) "$$p" "$(DESTDIR)$(bindir)/$$f" || exit 1; \ + else :; fi; \ + done + +uninstall-binPROGRAMS: + @$(NORMAL_UNINSTALL) + @list='$(bin_PROGRAMS)'; for p in $$list; do \ + f=`echo "$$p" | sed 's,^.*/,,;s/$(EXEEXT)$$//;$(transform);s/$$/$(EXEEXT)/'`; \ + echo " rm -f '$(DESTDIR)$(bindir)/$$f'"; \ + rm -f "$(DESTDIR)$(bindir)/$$f"; \ + done + +clean-binPROGRAMS: + @list='$(bin_PROGRAMS)'; for p in $$list; do \ + f=`echo $$p|sed 's/$(EXEEXT)$$//'`; \ + echo " rm -f $$p $$f"; \ + rm -f $$p $$f ; \ + done + +clean-noinstPROGRAMS: + @list='$(noinst_PROGRAMS)'; for p in $$list; do \ + f=`echo $$p|sed 's/$(EXEEXT)$$//'`; \ + echo " rm -f $$p $$f"; \ + rm -f $$p $$f ; \ + done +dftables$(EXEEXT): $(dftables_OBJECTS) $(dftables_DEPENDENCIES) + @rm -f dftables$(EXEEXT) + $(LINK) $(dftables_OBJECTS) $(dftables_LDADD) $(LIBS) +pcre_scanner_unittest$(EXEEXT): $(pcre_scanner_unittest_OBJECTS) $(pcre_scanner_unittest_DEPENDENCIES) + @rm -f pcre_scanner_unittest$(EXEEXT) + $(CXXLINK) $(pcre_scanner_unittest_OBJECTS) $(pcre_scanner_unittest_LDADD) $(LIBS) +pcre_stringpiece_unittest$(EXEEXT): $(pcre_stringpiece_unittest_OBJECTS) $(pcre_stringpiece_unittest_DEPENDENCIES) + @rm -f pcre_stringpiece_unittest$(EXEEXT) + $(CXXLINK) $(pcre_stringpiece_unittest_OBJECTS) $(pcre_stringpiece_unittest_LDADD) $(LIBS) +pcrecpp_unittest$(EXEEXT): $(pcrecpp_unittest_OBJECTS) $(pcrecpp_unittest_DEPENDENCIES) + @rm -f pcrecpp_unittest$(EXEEXT) + $(CXXLINK) $(pcrecpp_unittest_OBJECTS) $(pcrecpp_unittest_LDADD) $(LIBS) +pcregrep$(EXEEXT): $(pcregrep_OBJECTS) $(pcregrep_DEPENDENCIES) + @rm -f pcregrep$(EXEEXT) + $(LINK) $(pcregrep_OBJECTS) $(pcregrep_LDADD) $(LIBS) +pcretest$(EXEEXT): $(pcretest_OBJECTS) $(pcretest_DEPENDENCIES) + @rm -f pcretest$(EXEEXT) + $(LINK) $(pcretest_OBJECTS) $(pcretest_LDADD) $(LIBS) +install-binSCRIPTS: $(bin_SCRIPTS) + @$(NORMAL_INSTALL) + test -z "$(bindir)" || $(MKDIR_P) "$(DESTDIR)$(bindir)" + @list='$(bin_SCRIPTS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + if test -f $$d$$p; then \ + f=`echo "$$p" | sed 's|^.*/||;$(transform)'`; \ + echo " $(binSCRIPT_INSTALL) '$$d$$p' '$(DESTDIR)$(bindir)/$$f'"; \ + $(binSCRIPT_INSTALL) "$$d$$p" "$(DESTDIR)$(bindir)/$$f"; \ + else :; fi; \ + done + +uninstall-binSCRIPTS: + @$(NORMAL_UNINSTALL) + @list='$(bin_SCRIPTS)'; for p in $$list; do \ + f=`echo "$$p" | sed 's|^.*/||;$(transform)'`; \ + echo " rm -f '$(DESTDIR)$(bindir)/$$f'"; \ + rm -f "$(DESTDIR)$(bindir)/$$f"; \ + done + +mostlyclean-compile: + -rm -f *.$(OBJEXT) + +distclean-compile: + -rm -f *.tab.c + +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/dftables.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_chartables.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_compile.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_config.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_dfa_exec.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_exec.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_fullinfo.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_get.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_globals.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_info.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_maketables.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_newline.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_ord2utf8.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_refcount.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_scanner.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_scanner_unittest.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_stringpiece.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_stringpiece_unittest.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_study.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_tables.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_try_flipped.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_ucd.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_valid_utf8.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_version.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcre_xclass.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcrecpp.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcrecpp_unittest.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcregrep.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcreposix.Plo@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcretest.Po@am__quote@ + +.c.o: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCC_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c $< + +.c.obj: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ `$(CYGPATH_W) '$<'` +@am__fastdepCC_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c `$(CYGPATH_W) '$<'` + +.c.lo: +@am__fastdepCC_TRUE@ $(LTCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCC_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Plo +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(LTCOMPILE) -c -o $@ $< + +.cc.o: +@am__fastdepCXX_TRUE@ $(CXXCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCXX_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ DEPDIR=$(DEPDIR) $(CXXDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCXX_FALSE@ $(CXXCOMPILE) -c -o $@ $< + +.cc.obj: +@am__fastdepCXX_TRUE@ $(CXXCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ `$(CYGPATH_W) '$<'` +@am__fastdepCXX_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ DEPDIR=$(DEPDIR) $(CXXDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCXX_FALSE@ $(CXXCOMPILE) -c -o $@ `$(CYGPATH_W) '$<'` + +.cc.lo: +@am__fastdepCXX_TRUE@ $(LTCXXCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCXX_TRUE@ mv -f $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Plo +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ source='$<' object='$@' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ DEPDIR=$(DEPDIR) $(CXXDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCXX_FALSE@ $(LTCXXCOMPILE) -c -o $@ $< + +mostlyclean-libtool: + -rm -f *.lo + +clean-libtool: + -rm -rf .libs _libs + +distclean-libtool: + -rm -f libtool +install-man1: $(man1_MANS) $(man_MANS) + @$(NORMAL_INSTALL) + test -z "$(man1dir)" || $(MKDIR_P) "$(DESTDIR)$(man1dir)" + @list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \ + l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \ + for i in $$l2; do \ + case "$$i" in \ + *.1*) list="$$list $$i" ;; \ + esac; \ + done; \ + for i in $$list; do \ + if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \ + else file=$$i; fi; \ + ext=`echo $$i | sed -e 's/^.*\\.//'`; \ + case "$$ext" in \ + 1*) ;; \ + *) ext='1' ;; \ + esac; \ + inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \ + inst=`echo $$inst | sed -e 's/^.*\///'`; \ + inst=`echo $$inst | sed '$(transform)'`.$$ext; \ + echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man1dir)/$$inst'"; \ + $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man1dir)/$$inst"; \ + done +uninstall-man1: + @$(NORMAL_UNINSTALL) + @list='$(man1_MANS) $(dist_man1_MANS) $(nodist_man1_MANS)'; \ + l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \ + for i in $$l2; do \ + case "$$i" in \ + *.1*) list="$$list $$i" ;; \ + esac; \ + done; \ + for i in $$list; do \ + ext=`echo $$i | sed -e 's/^.*\\.//'`; \ + case "$$ext" in \ + 1*) ;; \ + *) ext='1' ;; \ + esac; \ + inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \ + inst=`echo $$inst | sed -e 's/^.*\///'`; \ + inst=`echo $$inst | sed '$(transform)'`.$$ext; \ + echo " rm -f '$(DESTDIR)$(man1dir)/$$inst'"; \ + rm -f "$(DESTDIR)$(man1dir)/$$inst"; \ + done +install-man3: $(man3_MANS) $(man_MANS) + @$(NORMAL_INSTALL) + test -z "$(man3dir)" || $(MKDIR_P) "$(DESTDIR)$(man3dir)" + @list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \ + l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \ + for i in $$l2; do \ + case "$$i" in \ + *.3*) list="$$list $$i" ;; \ + esac; \ + done; \ + for i in $$list; do \ + if test -f $(srcdir)/$$i; then file=$(srcdir)/$$i; \ + else file=$$i; fi; \ + ext=`echo $$i | sed -e 's/^.*\\.//'`; \ + case "$$ext" in \ + 3*) ;; \ + *) ext='3' ;; \ + esac; \ + inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \ + inst=`echo $$inst | sed -e 's/^.*\///'`; \ + inst=`echo $$inst | sed '$(transform)'`.$$ext; \ + echo " $(INSTALL_DATA) '$$file' '$(DESTDIR)$(man3dir)/$$inst'"; \ + $(INSTALL_DATA) "$$file" "$(DESTDIR)$(man3dir)/$$inst"; \ + done +uninstall-man3: + @$(NORMAL_UNINSTALL) + @list='$(man3_MANS) $(dist_man3_MANS) $(nodist_man3_MANS)'; \ + l2='$(man_MANS) $(dist_man_MANS) $(nodist_man_MANS)'; \ + for i in $$l2; do \ + case "$$i" in \ + *.3*) list="$$list $$i" ;; \ + esac; \ + done; \ + for i in $$list; do \ + ext=`echo $$i | sed -e 's/^.*\\.//'`; \ + case "$$ext" in \ + 3*) ;; \ + *) ext='3' ;; \ + esac; \ + inst=`echo $$i | sed -e 's/\\.[0-9a-z]*$$//'`; \ + inst=`echo $$inst | sed -e 's/^.*\///'`; \ + inst=`echo $$inst | sed '$(transform)'`.$$ext; \ + echo " rm -f '$(DESTDIR)$(man3dir)/$$inst'"; \ + rm -f "$(DESTDIR)$(man3dir)/$$inst"; \ + done +install-dist_docDATA: $(dist_doc_DATA) + @$(NORMAL_INSTALL) + test -z "$(docdir)" || $(MKDIR_P) "$(DESTDIR)$(docdir)" + @list='$(dist_doc_DATA)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(dist_docDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(docdir)/$$f'"; \ + $(dist_docDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(docdir)/$$f"; \ + done + +uninstall-dist_docDATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_doc_DATA)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(docdir)/$$f'"; \ + rm -f "$(DESTDIR)$(docdir)/$$f"; \ + done +install-dist_htmlDATA: $(dist_html_DATA) + @$(NORMAL_INSTALL) + test -z "$(htmldir)" || $(MKDIR_P) "$(DESTDIR)$(htmldir)" + @list='$(dist_html_DATA)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(dist_htmlDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(htmldir)/$$f'"; \ + $(dist_htmlDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(htmldir)/$$f"; \ + done + +uninstall-dist_htmlDATA: + @$(NORMAL_UNINSTALL) + @list='$(dist_html_DATA)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(htmldir)/$$f'"; \ + rm -f "$(DESTDIR)$(htmldir)/$$f"; \ + done +install-htmlDATA: $(html_DATA) + @$(NORMAL_INSTALL) + test -z "$(htmldir)" || $(MKDIR_P) "$(DESTDIR)$(htmldir)" + @list='$(html_DATA)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(htmlDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(htmldir)/$$f'"; \ + $(htmlDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(htmldir)/$$f"; \ + done + +uninstall-htmlDATA: + @$(NORMAL_UNINSTALL) + @list='$(html_DATA)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(htmldir)/$$f'"; \ + rm -f "$(DESTDIR)$(htmldir)/$$f"; \ + done +install-pkgconfigDATA: $(pkgconfig_DATA) + @$(NORMAL_INSTALL) + test -z "$(pkgconfigdir)" || $(MKDIR_P) "$(DESTDIR)$(pkgconfigdir)" + @list='$(pkgconfig_DATA)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(pkgconfigDATA_INSTALL) '$$d$$p' '$(DESTDIR)$(pkgconfigdir)/$$f'"; \ + $(pkgconfigDATA_INSTALL) "$$d$$p" "$(DESTDIR)$(pkgconfigdir)/$$f"; \ + done + +uninstall-pkgconfigDATA: + @$(NORMAL_UNINSTALL) + @list='$(pkgconfig_DATA)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(pkgconfigdir)/$$f'"; \ + rm -f "$(DESTDIR)$(pkgconfigdir)/$$f"; \ + done +install-includeHEADERS: $(include_HEADERS) + @$(NORMAL_INSTALL) + test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)" + @list='$(include_HEADERS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(includeHEADERS_INSTALL) '$$d$$p' '$(DESTDIR)$(includedir)/$$f'"; \ + $(includeHEADERS_INSTALL) "$$d$$p" "$(DESTDIR)$(includedir)/$$f"; \ + done + +uninstall-includeHEADERS: + @$(NORMAL_UNINSTALL) + @list='$(include_HEADERS)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(includedir)/$$f'"; \ + rm -f "$(DESTDIR)$(includedir)/$$f"; \ + done +install-nodist_includeHEADERS: $(nodist_include_HEADERS) + @$(NORMAL_INSTALL) + test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)" + @list='$(nodist_include_HEADERS)'; for p in $$list; do \ + if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ + f=$(am__strip_dir) \ + echo " $(nodist_includeHEADERS_INSTALL) '$$d$$p' '$(DESTDIR)$(includedir)/$$f'"; \ + $(nodist_includeHEADERS_INSTALL) "$$d$$p" "$(DESTDIR)$(includedir)/$$f"; \ + done + +uninstall-nodist_includeHEADERS: + @$(NORMAL_UNINSTALL) + @list='$(nodist_include_HEADERS)'; for p in $$list; do \ + f=$(am__strip_dir) \ + echo " rm -f '$(DESTDIR)$(includedir)/$$f'"; \ + rm -f "$(DESTDIR)$(includedir)/$$f"; \ + done + +ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES) + list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + mkid -fID $$unique +tags: TAGS + +TAGS: $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + tags=; \ + here=`pwd`; \ + list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \ + test -n "$$unique" || unique=$$empty_fix; \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + $$tags $$unique; \ + fi +ctags: CTAGS +CTAGS: $(HEADERS) $(SOURCES) config.h.in $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + tags=; \ + here=`pwd`; \ + list='$(SOURCES) $(HEADERS) config.h.in $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) ' { files[$$0] = 1; } \ + END { for (i in files) print i; }'`; \ + test -z "$(CTAGS_ARGS)$$tags$$unique" \ + || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \ + $$tags $$unique + +GTAGS: + here=`$(am__cd) $(top_builddir) && pwd` \ + && cd $(top_srcdir) \ + && gtags -i $(GTAGS_ARGS) $$here + +distclean-tags: + -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags + +check-TESTS: $(TESTS) + @failed=0; all=0; xfail=0; xpass=0; skip=0; ws='[ ]'; \ + srcdir=$(srcdir); export srcdir; \ + list=' $(TESTS) '; \ + if test -n "$$list"; then \ + for tst in $$list; do \ + if test -f ./$$tst; then dir=./; \ + elif test -f $$tst; then dir=; \ + else dir="$(srcdir)/"; fi; \ + if $(TESTS_ENVIRONMENT) $${dir}$$tst; then \ + all=`expr $$all + 1`; \ + case " $(XFAIL_TESTS) " in \ + *$$ws$$tst$$ws*) \ + xpass=`expr $$xpass + 1`; \ + failed=`expr $$failed + 1`; \ + echo "XPASS: $$tst"; \ + ;; \ + *) \ + echo "PASS: $$tst"; \ + ;; \ + esac; \ + elif test $$? -ne 77; then \ + all=`expr $$all + 1`; \ + case " $(XFAIL_TESTS) " in \ + *$$ws$$tst$$ws*) \ + xfail=`expr $$xfail + 1`; \ + echo "XFAIL: $$tst"; \ + ;; \ + *) \ + failed=`expr $$failed + 1`; \ + echo "FAIL: $$tst"; \ + ;; \ + esac; \ + else \ + skip=`expr $$skip + 1`; \ + echo "SKIP: $$tst"; \ + fi; \ + done; \ + if test "$$failed" -eq 0; then \ + if test "$$xfail" -eq 0; then \ + banner="All $$all tests passed"; \ + else \ + banner="All $$all tests behaved as expected ($$xfail expected failures)"; \ + fi; \ + else \ + if test "$$xpass" -eq 0; then \ + banner="$$failed of $$all tests failed"; \ + else \ + banner="$$failed of $$all tests did not behave as expected ($$xpass unexpected passes)"; \ + fi; \ + fi; \ + dashes="$$banner"; \ + skipped=""; \ + if test "$$skip" -ne 0; then \ + skipped="($$skip tests were not run)"; \ + test `echo "$$skipped" | wc -c` -le `echo "$$banner" | wc -c` || \ + dashes="$$skipped"; \ + fi; \ + report=""; \ + if test "$$failed" -ne 0 && test -n "$(PACKAGE_BUGREPORT)"; then \ + report="Please report to $(PACKAGE_BUGREPORT)"; \ + test `echo "$$report" | wc -c` -le `echo "$$banner" | wc -c` || \ + dashes="$$report"; \ + fi; \ + dashes=`echo "$$dashes" | sed s/./=/g`; \ + echo "$$dashes"; \ + echo "$$banner"; \ + test -z "$$skipped" || echo "$$skipped"; \ + test -z "$$report" || echo "$$report"; \ + echo "$$dashes"; \ + test "$$failed" -eq 0; \ + else :; fi + +distdir: $(DISTFILES) + $(am__remove_distdir) + test -d $(distdir) || mkdir $(distdir) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \ + fi; \ + cp -pR $$d/$$file $(distdir)$$dir || exit 1; \ + else \ + test -f $(distdir)/$$file \ + || cp -p $$d/$$file $(distdir)/$$file \ + || exit 1; \ + fi; \ + done + -find $(distdir) -type d ! -perm -777 -exec chmod a+rwx {} \; -o \ + ! -type d ! -perm -444 -links 1 -exec chmod a+r {} \; -o \ + ! -type d ! -perm -400 -exec chmod a+r {} \; -o \ + ! -type d ! -perm -444 -exec $(install_sh) -c -m a+r {} {} \; \ + || chmod -R a+r $(distdir) +dist-gzip: distdir + tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz + $(am__remove_distdir) +dist-bzip2: distdir + tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2 + $(am__remove_distdir) + +dist-tarZ: distdir + tardir=$(distdir) && $(am__tar) | compress -c >$(distdir).tar.Z + $(am__remove_distdir) + +dist-shar: distdir + shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz + $(am__remove_distdir) +dist-zip: distdir + -rm -f $(distdir).zip + zip -rq $(distdir).zip $(distdir) + $(am__remove_distdir) + +dist dist-all: distdir + tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz + tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2 + -rm -f $(distdir).zip + zip -rq $(distdir).zip $(distdir) + $(am__remove_distdir) + +# This target untars the dist file and tries a VPATH configuration. Then +# it guarantees that the distribution is self-contained by making another +# tarfile. +distcheck: dist + case '$(DIST_ARCHIVES)' in \ + *.tar.gz*) \ + GZIP=$(GZIP_ENV) gunzip -c $(distdir).tar.gz | $(am__untar) ;;\ + *.tar.bz2*) \ + bunzip2 -c $(distdir).tar.bz2 | $(am__untar) ;;\ + *.tar.Z*) \ + uncompress -c $(distdir).tar.Z | $(am__untar) ;;\ + *.shar.gz*) \ + GZIP=$(GZIP_ENV) gunzip -c $(distdir).shar.gz | unshar ;;\ + *.zip*) \ + unzip $(distdir).zip ;;\ + esac + chmod -R a-w $(distdir); chmod a+w $(distdir) + mkdir $(distdir)/_build + mkdir $(distdir)/_inst + chmod a-w $(distdir) + dc_install_base=`$(am__cd) $(distdir)/_inst && pwd | sed -e 's,^[^:\\/]:[\\/],/,'` \ + && dc_destdir="$${TMPDIR-/tmp}/am-dc-$$$$/" \ + && cd $(distdir)/_build \ + && ../configure --srcdir=.. --prefix="$$dc_install_base" \ + $(DISTCHECK_CONFIGURE_FLAGS) \ + && $(MAKE) $(AM_MAKEFLAGS) \ + && $(MAKE) $(AM_MAKEFLAGS) dvi \ + && $(MAKE) $(AM_MAKEFLAGS) check \ + && $(MAKE) $(AM_MAKEFLAGS) install \ + && $(MAKE) $(AM_MAKEFLAGS) installcheck \ + && $(MAKE) $(AM_MAKEFLAGS) uninstall \ + && $(MAKE) $(AM_MAKEFLAGS) distuninstallcheck_dir="$$dc_install_base" \ + distuninstallcheck \ + && chmod -R a-w "$$dc_install_base" \ + && ({ \ + (cd ../.. && umask 077 && mkdir "$$dc_destdir") \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" install \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" uninstall \ + && $(MAKE) $(AM_MAKEFLAGS) DESTDIR="$$dc_destdir" \ + distuninstallcheck_dir="$$dc_destdir" distuninstallcheck; \ + } || { rm -rf "$$dc_destdir"; exit 1; }) \ + && rm -rf "$$dc_destdir" \ + && $(MAKE) $(AM_MAKEFLAGS) dist \ + && rm -rf $(DIST_ARCHIVES) \ + && $(MAKE) $(AM_MAKEFLAGS) distcleancheck + $(am__remove_distdir) + @(echo "$(distdir) archives ready for distribution: "; \ + list='$(DIST_ARCHIVES)'; for i in $$list; do echo $$i; done) | \ + sed -e 1h -e 1s/./=/g -e 1p -e 1x -e '$$p' -e '$$x' +distuninstallcheck: + @cd $(distuninstallcheck_dir) \ + && test `$(distuninstallcheck_listfiles) | wc -l` -le 1 \ + || { echo "ERROR: files left after uninstall:" ; \ + if test -n "$(DESTDIR)"; then \ + echo " (check DESTDIR support)"; \ + fi ; \ + $(distuninstallcheck_listfiles) ; \ + exit 1; } >&2 +distcleancheck: distclean + @if test '$(srcdir)' = . ; then \ + echo "ERROR: distcleancheck can only run from a VPATH build" ; \ + exit 1 ; \ + fi + @test `$(distcleancheck_listfiles) | wc -l` -eq 0 \ + || { echo "ERROR: files left in build directory after distclean:" ; \ + $(distcleancheck_listfiles) ; \ + exit 1; } >&2 +check-am: all-am + $(MAKE) $(AM_MAKEFLAGS) $(check_SCRIPTS) + $(MAKE) $(AM_MAKEFLAGS) check-TESTS +check: check-am +all-am: Makefile $(LTLIBRARIES) $(PROGRAMS) $(SCRIPTS) $(MANS) $(DATA) \ + $(HEADERS) config.h +install-binPROGRAMS: install-libLTLIBRARIES + +installdirs: + for dir in "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" "$(DESTDIR)$(bindir)" "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(man3dir)" "$(DESTDIR)$(docdir)" "$(DESTDIR)$(htmldir)" "$(DESTDIR)$(htmldir)" "$(DESTDIR)$(pkgconfigdir)" "$(DESTDIR)$(includedir)" "$(DESTDIR)$(includedir)"; do \ + test -z "$$dir" || $(MKDIR_P) "$$dir"; \ + done +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + `test -z '$(STRIP)' || \ + echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install +mostlyclean-generic: + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +clean: clean-am + +clean-am: clean-binPROGRAMS clean-generic clean-libLTLIBRARIES \ + clean-libtool clean-noinstPROGRAMS mostlyclean-am + +distclean: distclean-am + -rm -f $(am__CONFIG_DISTCLEAN_FILES) + -rm -rf ./$(DEPDIR) + -rm -f Makefile +distclean-am: clean-am distclean-compile distclean-generic \ + distclean-hdr distclean-libtool distclean-tags + +dvi: dvi-am + +dvi-am: + +html: html-am + +info: info-am + +info-am: + +install-data-am: install-dist_docDATA install-dist_htmlDATA \ + install-htmlDATA install-includeHEADERS install-man \ + install-nodist_includeHEADERS install-pkgconfigDATA + +install-dvi: install-dvi-am + +install-exec-am: install-binPROGRAMS install-binSCRIPTS \ + install-libLTLIBRARIES + +install-html: install-html-am + +install-info: install-info-am + +install-man: install-man1 install-man3 + +install-pdf: install-pdf-am + +install-ps: install-ps-am + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f $(am__CONFIG_DISTCLEAN_FILES) + -rm -rf $(top_srcdir)/autom4te.cache + -rm -rf ./$(DEPDIR) + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-compile mostlyclean-generic \ + mostlyclean-libtool + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: uninstall-binPROGRAMS uninstall-binSCRIPTS \ + uninstall-dist_docDATA uninstall-dist_htmlDATA \ + uninstall-htmlDATA uninstall-includeHEADERS \ + uninstall-libLTLIBRARIES uninstall-man \ + uninstall-nodist_includeHEADERS uninstall-pkgconfigDATA + +uninstall-man: uninstall-man1 uninstall-man3 + +.MAKE: install-am install-strip + +.PHONY: CTAGS GTAGS all all-am am--refresh check check-TESTS check-am \ + clean clean-binPROGRAMS clean-generic clean-libLTLIBRARIES \ + clean-libtool clean-noinstPROGRAMS ctags dist dist-all \ + dist-bzip2 dist-gzip dist-shar dist-tarZ dist-zip distcheck \ + distclean distclean-compile distclean-generic distclean-hdr \ + distclean-libtool distclean-tags distcleancheck distdir \ + distuninstallcheck dvi dvi-am html html-am info info-am \ + install install-am install-binPROGRAMS install-binSCRIPTS \ + install-data install-data-am install-dist_docDATA \ + install-dist_htmlDATA install-dvi install-dvi-am install-exec \ + install-exec-am install-html install-html-am install-htmlDATA \ + install-includeHEADERS install-info install-info-am \ + install-libLTLIBRARIES install-man install-man1 install-man3 \ + install-nodist_includeHEADERS install-pdf install-pdf-am \ + install-pkgconfigDATA install-ps install-ps-am install-strip \ + installcheck installcheck-am installdirs maintainer-clean \ + maintainer-clean-generic mostlyclean mostlyclean-compile \ + mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \ + tags uninstall uninstall-am uninstall-binPROGRAMS \ + uninstall-binSCRIPTS uninstall-dist_docDATA \ + uninstall-dist_htmlDATA uninstall-htmlDATA \ + uninstall-includeHEADERS uninstall-libLTLIBRARIES \ + uninstall-man uninstall-man1 uninstall-man3 \ + uninstall-nodist_includeHEADERS uninstall-pkgconfigDATA + + +pcre.h.generic: configure.ac + rm -f $@ + cp -p pcre.h $@ + +@WITH_REBUILD_CHARTABLES_TRUE@pcre_chartables.c: dftables$(EXEEXT) +@WITH_REBUILD_CHARTABLES_TRUE@ ./dftables$(EXEEXT) $@ + +@WITH_REBUILD_CHARTABLES_FALSE@pcre_chartables.c: $(srcdir)/pcre_chartables.c.dist +@WITH_REBUILD_CHARTABLES_FALSE@ rm -f $@ +@WITH_REBUILD_CHARTABLES_FALSE@ $(LN_S) $(srcdir)/pcre_chartables.c.dist $@ + +# A compatibility line, the old build system worked with 'make test' +test: check ; + +# A PCRE user submitted the following addition, saying that it "will allow +# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a +# nice DLL for Windows use". +pcre.dll: $(DLL_OBJS) + $(CC) -shared -o pcre.dll -Wl,"--strip-all" -Wl,"--export-all-symbols" $(DLL_OBJS) +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: Modified: freeswitch/trunk/libs/pcre/NEWS ============================================================================== --- freeswitch/trunk/libs/pcre/NEWS (original) +++ freeswitch/trunk/libs/pcre/NEWS Mon Jun 8 18:51:30 2009 @@ -1,6 +1,168 @@ News about PCRE releases ------------------------ +Release 7.9 11-Apr-09 +--------------------- + +Mostly bugfixes and tidies with just a couple of minor functional additions. + + +Release 7.8 05-Sep-08 +--------------------- + +More bug fixes, plus a performance improvement in Unicode character property +lookup. + + +Release 7.7 07-May-08 +--------------------- + +This is once again mainly a bug-fix release, but there are a couple of new +features. + + +Release 7.6 28-Jan-08 +--------------------- + +The main reason for having this release so soon after 7.5 is because it fixes a +potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In +addition, the CMake configuration files have been brought up to date. + + +Release 7.5 10-Jan-08 +--------------------- + +This is mainly a bug-fix release. However the ability to link pcregrep with +libz or libbz2 and the ability to link pcretest with libreadline have been +added. Also the --line-offsets and --file-offsets options were added to +pcregrep. + + +Release 7.4 21-Sep-07 +--------------------- + +The only change of specification is the addition of options to control whether +\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. +Otherwise, the changes are bug fixes and a refactoring to reduce the number of +relocations needed in a shared library. There have also been some documentation +updates, in particular, some more information about using CMake to build PCRE +has been added to the NON-UNIX-USE file. + + +Release 7.3 28-Aug-07 +--------------------- + +Most changes are bug fixes. Some that are not: + +1. There is some support for Perl 5.10's experimental "backtracking control + verbs" such as (*PRUNE). + +2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more + restrictive in the strings it accepts. + +3. Checking for potential integer overflow has been made more dynamic, and as a + consequence there is no longer a hard limit on the size of a subpattern that + has a limited repeat count. + +4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec() + no longer advance by two characters instead of one when an unanchored match + fails at CRLF if there are explicit CR or LF matches within the pattern. + This gets rid of some anomalous effects that previously occurred. + +5. Some PCRE-specific settings for varying the newline options at the start of + a pattern have been added. + + +Release 7.2 19-Jun-07 +--------------------- + +WARNING: saved patterns that were compiled by earlier versions of PCRE must be +recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v, +and \V). + +Correction to the notes for 7.1: the note about shared libraries for Windows is +wrong. Previously, three libraries were built, but each could function +independently. For example, the pcreposix library also included all the +functions from the basic pcre library. The change is that the three libraries +are no longer independent. They are like the Unix libraries. To use the +pcreposix functions, for example, you need to link with both the pcreposix and +the basic pcre library. + +Some more features from Perl 5.10 have been added: + + (?-n) and (?+n) relative references for recursion and subroutines. + + (?(-n) and (?(+n) relative references as conditions. + + \k{name} and \g{name} are synonyms for \k<name>. + + \K to reset the start of the matched string; for example, (foo)\Kbar + matches bar preceded by foo, but only sets bar as the matched string. + + (?| introduces a group where the capturing parentheses in each alternative + start from the same number; for example, (?|(abc)|(xyz)) sets capturing + parentheses number 1 in both cases. + + \h, \H, \v, \V match horizontal and vertical whitespace, respectively. + + +Release 7.1 24-Apr-07 +--------------------- + +There is only one new feature in this release: a linebreak setting of +PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which +recognizes only CRLF, CR, and LF as linebreaks. + +A few bugs are fixed (see ChangeLog for details), but the major change is a +complete re-implementation of the build system. This now has full Autotools +support and so is now "standard" in some sense. It should help with compiling +PCRE in a wide variety of environments. + +NOTE: when building shared libraries for Windows, three dlls are now built, +called libpcre, libpcreposix, and libpcrecpp. Previously, everything was +included in a single dll. + +Another important change is that the dftables auxiliary program is no longer +compiled and run at "make" time by default. Instead, a default set of character +tables (assuming ASCII coding) is used. If you want to use dftables to generate +the character tables as previously, add --enable-rebuild-chartables to the +"configure" command. You must do this if you are compiling PCRE to run on a +system that uses EBCDIC code. + +There is a discussion about character tables in the README file. The default is +not to use dftables so that that there is no problem when cross-compiling. + + +Release 7.0 19-Dec-06 +--------------------- + +This release has a new major number because there have been some internal +upheavals to facilitate the addition of new optimizations and other facilities, +and to make subsequent maintenance and extension easier. Compilation is likely +to be a bit slower, but there should be no major effect on runtime performance. +Previously compiled patterns are NOT upwards compatible with this release. If +you have saved compiled patterns from a previous release, you will have to +re-compile them. Important changes that are visible to users are: + +1. The Unicode property tables have been updated to Unicode 5.0.0, which adds + some more scripts. + +2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline + sequence as a newline. + +3. The \R escape matches a single Unicode newline sequence as a single unit. + +4. New features that will appear in Perl 5.10 are now in PCRE. These include + alternative Perl syntax for named parentheses, and Perl syntax for + recursion. + +5. The C++ wrapper interface has been extended by the addition of a + QuoteMeta function and the ability to allow copy construction and + assignment. + +For a complete list of changes, see the ChangeLog file. + + Release 6.7 04-Jul-06 --------------------- Modified: freeswitch/trunk/libs/pcre/NON-UNIX-USE ============================================================================== --- freeswitch/trunk/libs/pcre/NON-UNIX-USE (original) +++ freeswitch/trunk/libs/pcre/NON-UNIX-USE Mon Jun 8 18:51:30 2009 @@ -1,127 +1,154 @@ Compiling PCRE on non-Unix systems ---------------------------------- -See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel) -have no knowledge of Windows or VMS sytems and how their libraries work. The -items in the PCRE Makefile that relate to anything other than Unix-like systems -have been contributed by PCRE users. There are some other comments and files in -the Contrib directory on the ftp site that you may find useful. See +This document contains the following sections: - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + General + Generic instructions for the PCRE C library + The C++ wrapper functions + Building for virtual Pascal + Stack size in Windows environments + Linking programs in Windows environments + Comments about Win32 builds + Building PCRE on Windows with CMake + Use of relative paths with CMake on Windows + Testing with runtest.bat + Building under Windows with BCC5.5 + Building PCRE on OpenVMS + + +GENERAL + +I (Philip Hazel) have no experience of Windows or VMS sytems and how their +libraries work. The items in the PCRE distribution and Makefile that relate to +anything other than Unix-like systems are untested by me. + +There are some other comments and files (including some documentation in CHM +format) in the Contrib directory on the FTP site: -If you want to compile PCRE for a non-Unix system (or perhaps, more strictly, -for a system that does not support "configure" and "make" files), note that -the basic PCRE library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. The C++ wrapper functions are a separate issue (see below). - - -GENERIC INSTRUCTIONS FOR THE C LIBRARY - -The following are generic comments about building PCRE. The interspersed -indented commands are suggestions from Mark Tetrode as to which commands you -might use on a Windows system to build a static library. - -(1) Copy or rename the file config.in as config.h, and change the macros that -define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. -Unfortunately, because of the way Unix autoconf works, the default setting has -to be 0. You may also want to make changes to other macros in config.h. In -particular, if you want to force a specific value for newline, you can define -the NEWLINE macro. The default is to use '\n', thereby using whatever value -your compiler gives to '\n'. - - rem Mark Tetrode's commands - copy config.in config.h - rem Use write, because notepad cannot handle UNIX files. Change values. - write config.h - -(2) Compile dftables.c as a stand-alone program, and then run it with -the single argument "pcre_chartables.c". This generates a set of standard -character tables and writes them to that file. - - rem Mark Tetrode's commands - rem Compile & run - cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c - dftables.exe pcre_chartables.c - -(3) Compile the following source files: - - pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_info.c - pcre_maketables.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_study.c - pcre_tables.c - pcre_try_flipped.c - pcre_ucp_searchfuncs.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c - -and link them all together into an object library in whichever form your system -keeps such libraries. This is the pcre C library. If your system has static and -shared libraries, you may have to do this once for each type. - - rem These comments are out-of-date, referring to a previous release which - rem had fewer source files. Replace with the file names from above. - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c - lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj - -(4) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix -library. - - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c - lib /OUT:pcreposix.lib pcreposix.obj - -(5) Compile the test program pcretest.c. This needs the functions in the -pcre and pcreposix libraries when linking. - - rem Mark Tetrode's commands - rem compile & link - cl /F0x400000 pcretest.c pcre.lib pcreposix.lib - -(6) Run pcretest on the testinput files in the testdata directory, and check -that the output matches the corresponding testoutput files. You must use the --i option when checking testinput2. Note that the supplied files are in Unix -format, with just LF characters as line terminators. You may need to edit them -to change this if your system uses a different convention. - - rem Mark Tetrode's commands - pcretest testdata\testinput1 testdata\myoutput1 - windiff testdata\testoutput1 testdata\myoutput1 - pcretest -i testdata\testinput2 testdata\myoutput2 - windiff testdata\testoutput2 testdata\myoutput2 - pcretest testdata\testinput3 testdata\myoutput3 - windiff testdata\testoutput3 testdata\myoutput3 - pcretest testdata\testinput4 testdata\myoutput4 - windiff testdata\testoutput4 testdata\myoutput4 - pcretest testdata\testinput5 testdata\myoutput5 - windiff testdata\testoutput5 testdata\myoutput5 - pcretest testdata\testinput6 testdata\myoutput6 - windiff testdata\testoutput6 testdata\myoutput6 + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib -Note that there are now three more tests (7, 8, 9) that did not exist when Mark -wrote those comments. The test the new pcre_dfa_exec() function. +If you want to compile PCRE for a non-Unix system (especially for a system that +does not support "configure" and "make" files), note that the basic PCRE +library consists entirely of code written in Standard C, and so should compile +successfully on any system that has a Standard C compiler and library. The C++ +wrapper functions are a separate issue (see below). + +The PCRE distribution includes a "configure" file for use by the Configure/Make +build system, as found in many Unix-like environments. There is also support +support for CMake, which some users prefer, in particular in Windows +environments. There are some instructions for CMake under Windows in the +section entitled "Building PCRE with CMake" below. CMake can also be used to +build PCRE in Unix-like systems. + + +GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY + +The following are generic comments about building the PCRE C library "by hand". + + (1) Copy or rename the file config.h.generic as config.h, and edit the macro + settings that it contains to whatever is appropriate for your environment. + In particular, if you want to force a specific value for newline, you can + define the NEWLINE macro. When you compile any of the PCRE modules, you + must specify -DHAVE_CONFIG_H to your compiler so that config.h is included + in the sources. + + An alternative approach is not to edit config.h, but to use -D on the + compiler command line to make any changes that you need to the + configuration options. In this case -DHAVE_CONFIG_H must not be set. + + NOTE: There have been occasions when the way in which certain parameters + in config.h are used has changed between releases. (In the configure/make + world, this is handled automatically.) When upgrading to a new release, + you are strongly advised to review config.h.generic before re-using what + you had previously. + + (2) Copy or rename the file pcre.h.generic as pcre.h. + + (3) EITHER: + Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. + + OR: + Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if + you have set up config.h), and then run it with the single argument + "pcre_chartables.c". This generates a set of standard character tables + and writes them to that file. The tables are generated using the default + C locale for your system. If you want to use a locale that is specified + by LC_xxx environment variables, add the -L option to the dftables + command. You must use this method if you are building on a system that + uses EBCDIC code. + + The tables in pcre_chartables.c are defaults. The caller of PCRE can + specify alternative tables at run time. + + (4) Ensure that you have the following header files: + + pcre_internal.h + ucp.h + + (5) Also ensure that you have the following file, which is #included as source + when building a debugging version of PCRE, and is also used by pcretest. + + pcre_printint.src + + (6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler + option if you have set up config.h with your configuration, or else use + other -D settings to change the configuration as required. + + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_info.c + pcre_maketables.c + pcre_newline.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_study.c + pcre_tables.c + pcre_try_flipped.c + pcre_ucd.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c + + Make sure that you include -I. in the compiler command (or equivalent for + an unusual compiler) so that all included PCRE header files are first + sought in the current directory. Otherwise you run the risk of picking up + a previously-installed file from somewhere else. + + (7) Now link all the compiled code into an object library in whichever form + your system keeps such libraries. This is the basic PCRE C library. If + your system has static and shared libraries, you may have to do this once + for each type. + + (8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary) + and link the result (on its own) as the pcreposix library. + + (9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H). + This needs the functions in the pcre and pcreposix libraries when linking. + It also needs the pcre_printint.src source file, which it #includes. + +(10) Run pcretest on the testinput files in the testdata directory, and check + that the output matches the corresponding testoutput files. Note that the + supplied files are in Unix format, with just LF characters as line + terminators. You may need to edit them to change this if your system uses + a different convention. If you are using Windows, you probably should use + the wintestinput3 file instead of testinput3 (and the corresponding output + file). This is a locale test; wintestinput3 sets the locale to "french" + rather than "fr_FR", and there some minor output differences. -(7) If you want to use the pcregrep command, compile and link pcregrep.c; it -uses only the basic PCRE library. +(11) If you want to use the pcregrep command, compile and link pcregrep.c; it + uses only the basic PCRE library (it does not need the pcreposix library). THE C++ WRAPPER FUNCTIONS -The PCRE distribution now contains some C++ wrapper functions and tests, +The PCRE distribution also contains some C++ wrapper functions and tests, contributed by Google Inc. On a system that can use "configure" and "make", the functions are automatically built into a library called pcrecpp. It should be straightforward to compile the .cc files manually on other systems. The @@ -129,77 +156,228 @@ xxx.cc files. -FURTHER REMARKS - -If you have a system without "configure" but where you can use a Makefile, edit -Makefile.in to create Makefile, substituting suitable values for the variables -at the head of the file. - -Some help in building a Win32 DLL of PCRE in GnuWin32 environments was -contributed by Paul Sokolovsky. These environments are Mingw32 -(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin -(http://sourceware.cygnus.com/cygwin/). Paul comments: - - For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get - pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically - linked pgrep and pcretest. If you have /bin/sh, run RunTest (three - main test go ok, locale not supported). - -Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox -<sailorFred@yahoo.com>, who comments as follows: - - If you are using the PCRE DLL, the normal Unix style configure && make && - make check && make install should just work[*]. If you want to statically - link against the .a file, you must define PCRE_STATIC before including - pcre.h, otherwise the pcre_malloc and pcre_free exported functions will be - declared __declspec(dllimport), with hilarious results. See the configure.in - and pcretest.c for how it is done for the static test. - - Also, there will only be a libpcre.la, not a libpcreposix.la, as you - would expect from the Unix version. The single DLL includes the pcreposix - interface. - -[*] But note that the supplied test files are in Unix format, with just LF -characters as line terminators. You will have to edit them to change to CR LF -terminators. +BUILDING FOR VIRTUAL PASCAL A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. It is called makevp.bat. +was contributed by Alexander Tokarev. Stefan Weber updated the script and added +additional files. The following files in the distribution are for building PCRE +for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. -These are some further comments about Win32 builds from Mark Evans. They -were contributed before Fred Cox's changes were made, so it is possible that -they may no longer be relevant. - -"The documentation for Win32 builds is a bit shy. Under MSVC6 I -followed their instructions to the letter, but there were still -some things missing. - -(1) Must #define STATIC for entire project if linking statically. - (I see no reason to use DLLs for code this compact.) This of - course is a project setting in MSVC under Preprocessor. - -(2) Missing some #ifdefs relating to the function pointers - pcre_malloc and pcre_free. See my solution below. (The stubs - may not be mandatory but they made me feel better.)" -========================= -#ifdef _WIN32 -#include <malloc.h> +STACK SIZE IN WINDOWS ENVIRONMENTS -void* malloc_stub(size_t N) -{ return malloc(N); } -void free_stub(void* p) -{ free(p); } -void *(*pcre_malloc)(size_t) = &malloc_stub; -void (*pcre_free)(void *) = &free_stub; +The default processor stack size of 1Mb in some Windows environments is too +small for matching patterns that need much recursion. In particular, test 2 may +fail because of this. Normally, running out of stack causes a crash, but there +have been cases where the test program has just died silently. See your linker +documentation for how to increase stack size if you experience problems. The +Linux default of 8Mb is a reasonable choice for the stack, though even that can +be too small for some pattern/subject combinations. -#else +PCRE has a compile configuration option to disable the use of stack for +recursion so that heap is used instead. However, pattern matching is +significantly slower when this is done. There is more about stack usage in the +"pcrestack" documentation. -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; -#endif -========================= +LINKING PROGRAMS IN WINDOWS ENVIRONMENTS + +If you want to statically link a program against a PCRE library in the form of +a non-dll .a file, you must define PCRE_STATIC before including pcre.h, +otherwise the pcre_malloc() and pcre_free() exported functions will be declared +__declspec(dllimport), with unwanted results. + + +CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS + +It is possible to compile programs to use different calling conventions using +MSVC. Search the web for "calling conventions" for more information. To make it +easier to change the calling convention for the exported functions in the +PCRE library, the macro PCRE_CALL_CONVENTION is present in all the external +definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is +not set, it defaults to empty; the default calling convention is then used +(which is what is wanted most of the time). + + +COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below) + +There are two ways of building PCRE using the "configure, make, make install" +paradigm on Windows systems: using MinGW or using Cygwin. These are not at all +the same thing; they are completely different from each other. There is also +support for building using CMake, which some users find a more straightforward +way of building PCRE under Windows. However, the tests are not run +automatically when CMake is used. + +The MinGW home page (http://www.mingw.org/) says this: + + MinGW: A collection of freely available and freely distributable Windows + specific header files and import libraries combined with GNU toolsets that + allow one to produce native Windows programs that do not rely on any + 3rd-party C runtime DLLs. + +The Cygwin home page (http://www.cygwin.com/) says this: + + Cygwin is a Linux-like environment for Windows. It consists of two parts: + + . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing + substantial Linux API functionality + + . A collection of tools which provide Linux look and feel. + + The Cygwin DLL currently works with all recent, commercially released x86 32 + bit and 64 bit versions of Windows, with the exception of Windows CE. + +On both MinGW and Cygwin, PCRE should build correctly using: + + ./configure && make && make install + +This should create two libraries called libpcre and libpcreposix, and, if you +have enabled building the C++ wrapper, a third one called libpcrecpp. These are +independent libraries: when you like with libpcreposix or libpcrecpp you must +also link with libpcre, which contains the basic functions. (Some earlier +releases of PCRE included the basic libpcre functions in libpcreposix. This no +longer happens.) + +A user submitted a special-purpose patch that makes it easy to create +"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" +as a special target. If you use this target, no other files are built, and in +particular, the pcretest and pcregrep programs are not built. An example of how +this might be used is: + + ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll + +Using Cygwin's compiler generates libraries and executables that depend on +cygwin1.dll. If a library that is generated this way is distributed, +cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL +licence, this forces not only PCRE to be under the GPL, but also the entire +application. A distributor who wants to keep their own code proprietary must +purchase an appropriate Cygwin licence. + +MinGW has no such restrictions. The MinGW compiler generates a library or +executable that can run standalone on Windows without any third party dll or +licensing issues. + +But there is more complication: + +If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is +to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a +front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's +gcc and MinGW's gcc). So, a user can: + +. Build native binaries by using MinGW or by getting Cygwin and using + -mno-cygwin. + +. Build binaries that depend on cygwin1.dll by using Cygwin with the normal + compiler flags. + +The test files that are supplied with PCRE are in Unix format, with LF +characters as line terminators. It may be necessary to change the line +terminators in order to get some of the tests to work. We hope to improve +things in this area in future. + + +BUILDING PCRE ON WINDOWS WITH CMAKE + +CMake is an alternative build facility that can be used instead of the +traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles, +MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio +6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions +were contributed by a PCRE user. + +1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure + that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE source tree into a source + directory such as C:\pcre. + +3. Create a new, empty build directory: C:\pcre\build\ + +4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys + for Msys/MinGW or Visual Studio Command Prompt for VC/VC++ + +5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build + directories, respectively + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual Studio, + MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where you can + enable UTF-8 support, etc. + +9. Hit "Configure" again. The adjacent "OK" button should now be active. + +10. Hit "OK". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. + + +USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS + +A PCRE user comments as follows: + +I thought that others may want to know the current state of +CMAKE_USE_RELATIVE_PATHS support on Windows. + +Here it is: +-- AdditionalIncludeDirectories is only partially modified (only the +first path - see below) +-- Only some of the contained file paths are modified - shown below for +pcre.vcproj +-- It properly modifies + +I am sure CMake people can fix that if they want to. Until then one will +need to replace existing absolute paths in project files with relative +paths manually (e.g. from VS) - relative to project file location. I did +just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big +deal. + +AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" +AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" + +RelativePath="pcre.h"> +RelativePath="pcre_chartables.c"> +RelativePath="pcre_chartables.c.rule"> + + +TESTING WITH RUNTEST.BAT + +1. Copy RunTest.bat into the directory where pcretest.exe has been created. + +2. Edit RunTest.bat and insert a line that indentifies the relative location of + the pcre source, e.g.: + + set srcdir=..\pcre-7.4-RC3 + +3. Run RunTest.bat from a command shell environment. Test outputs will + automatically be compared to expected results, and discrepancies will + identified in the console output. + +4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and + pcre_scanner_unittest.exe. + + +BUILDING UNDER WINDOWS WITH BCC5.5 + +Michael Roy sent these comments about building PCRE under Windows with BCC5.5: + + Some of the core BCC libraries have a version of PCRE from 1998 built in, + which can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a + version mismatch. I'm including an easy workaround below, if you'd like to + include it in the non-unix instructions: + + When linking a project with BCC5.5, pcre.lib must be included before any of + the libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command + line. + + +BUILDING UNDER WINDOWS CE WITH VISUAL STUDIO 200x + +Vincent Richomme sent a zip archive of files to help with this process. They +can be found in the file "pcre-vsbuild.zip" in the Contrib directory of the FTP +site. BUILDING PCRE ON OPENVMS @@ -266,4 +444,5 @@ $! ========================= +Last Updated: 17 March 2009 **** Added: freeswitch/trunk/libs/pcre/PrepareRelease ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/PrepareRelease Mon Jun 8 18:51:30 2009 @@ -0,0 +1,214 @@ +#/bin/sh + +# Script to prepare the files for building a PCRE release. It does some +# processing of the documentation, detrails files, and creates pcre.h.generic +# and config.h.generic (for use by builders who can't run ./configure). + +# You must run this script before runnning "make dist". It makes use of the +# following files: + +# 132html A Perl script that converts a .1 or .3 man page into HTML. It +# is called from MakeRelease. It "knows" the relevant troff +# constructs that are used in the PCRE man pages. + +# CleanTxt A Perl script that cleans up the output of "nroff -man" by +# removing backspaces and other redundant text so as to produce +# a readable .txt file. + +# Detrail A Perl script that removes trailing spaces from files. + +# doc/index.html.src +# A file that is copied as index.html into the doc/html directory +# when the HTML documentation is built. It works like this so that +# doc/html can be deleted and re-created from scratch. + + +# First, sort out the documentation + +cd doc +echo Processing documentation + +# Make Text form of the documentation. It needs some mangling to make it +# tidy for online reading. Concatenate all the .3 stuff, but omit the +# individual function pages. + +cat <<End >pcre.txt +----------------------------------------------------------------------------- +This file contains a concatenation of the PCRE man pages, converted to plain +text format for ease of searching with a text editor, or for use on systems +that do not have a man page processor. The small individual files that give +synopses of each function in the library have not been included. There are +separate text files for the pcregrep and pcretest commands. +----------------------------------------------------------------------------- + + +End + +echo "Making pcre.txt" +for file in pcre pcrebuild pcrematching pcreapi pcrecallout pcrecompat \ + pcrepattern pcresyntax pcrepartial pcreprecompile \ + pcreperform pcreposix pcrecpp pcresample pcrestack ; do + echo " Processing $file.3" + nroff -c -man $file.3 >$file.rawtxt + ../CleanTxt <$file.rawtxt >>pcre.txt + /bin/rm $file.rawtxt + echo "------------------------------------------------------------------------------" >>pcre.txt + if [ "$file" != "pcresample" ] ; then + echo " " >>pcre.txt + echo " " >>pcre.txt + fi +done + +# The three commands +for file in pcretest pcregrep pcre-config ; do + echo Making $file.txt + nroff -c -man $file.1 >$file.rawtxt + ../CleanTxt <$file.rawtxt >$file.txt + /bin/rm $file.rawtxt +done + + +# Make HTML form of the documentation. + +echo "Making HTML documentation" +/bin/rm html/* +cp index.html.src html/index.html + +for file in *.1 ; do + base=`basename $file .1` + echo " Making $base.html" + ../132html -toc $base <$file >html/$base.html +done + +# Exclude table of contents for function summaries. It seems that expr +# forces an anchored regex. Also exclude them for small pages that have +# only one section. +for file in *.3 ; do + base=`basename $file .3` + toc=-toc + if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi + if [ "$base" = "pcresample" ] || \ + [ "$base" = "pcrestack" ] || \ + [ "$base" = "pcrecompat" ] || \ + [ "$base" = "pcreperform" ] ; then + toc="" + fi + echo " Making $base.html" + ../132html $toc $base <$file >html/$base.html + if [ $? != 0 ] ; then exit 1; fi +done + +# End of documentation processing + +cd .. +echo Documentation done + +# These files are detrailed; do not detrail the test data because there may be +# significant trailing spaces. The configure files are also omitted from the +# detrailing. + +files="\ + Makefile.am \ + Makefile.in \ + configure.ac \ + README \ + LICENCE \ + COPYING \ + AUTHORS \ + NEWS \ + NON-UNIX-USE \ + INSTALL \ + 132html \ + CleanTxt \ + Detrail \ + ChangeLog \ + CMakeLists.txt \ + RunGrepTest \ + RunTest \ + RunTest.bat \ + pcre-config.in \ + libpcre.pc.in \ + libpcrecpp.pc.in \ + config.h.in \ + pcre_printint.src \ + pcre_chartables.c.dist \ + pcredemo.c \ + pcregrep.c \ + pcretest.c \ + dftables.c \ + pcreposix.c \ + pcreposix.h \ + pcre.h.in \ + pcre_internal.h + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucp_searchfuncs.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + pcre_scanner.cc \ + pcre_scanner.h \ + pcre_scanner_unittest.cc \ + pcrecpp.cc \ + pcrecpp.h \ + pcrecpparg.h.in \ + pcrecpp_unittest.cc \ + pcre_stringpiece.cc \ + pcre_stringpiece.h.in \ + pcre_stringpiece_unittest.cc \ + perltest.pl \ + ucp.h \ + ucpinternal.h \ + ucptable.h \ + makevp.bat \ + pcre.def \ + libpcre.def \ + libpcreposix.def" + +echo Detrailing +./Detrail $files doc/p* doc/html/* + +echo Doing basic configure to get default pcre.h and config.h +# This is in case the caller has set aliases (as I do - PH) +unset cp ls mv rm +./configure >/dev/null + +echo Converting pcre.h and config.h to generic forms +cp -f pcre.h pcre.h.generic + +perl <<'END' + open(IN, "<config.h") || die "Can't open config.h: $!\n"; + open(OUT, ">config.h.generic") || die "Can't open config.h.generic: $!\n"; + while (<IN>) + { + if (/^#define\s(?!PACKAGE)(\w+)/) + { + print OUT "#ifndef $1\n"; + print OUT; + print OUT "#endif\n"; + } + else + { + print OUT; + } + } + close IN; + close OUT; +END + +echo Done + +#End Modified: freeswitch/trunk/libs/pcre/README ============================================================================== --- freeswitch/trunk/libs/pcre/README (original) +++ freeswitch/trunk/libs/pcre/README Mon Jun 8 18:51:30 2009 @@ -1,55 +1,93 @@ README file for PCRE (Perl-compatible regular expression library) ----------------------------------------------------------------- -The latest release of PCRE is always available from +The latest release of PCRE is always available in three alternative formats +from: ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2 + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip + +There is a mailing list for discussion about the development of PCRE at + + pcre-dev@exim.org Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE APIs + Documentation for PCRE + Contributions by users of PCRE + Building PCRE on non-Unix systems + Building PCRE on Unix-like systems + Retrieving configuration information on Unix-like systems + Shared libraries on Unix-like systems + Cross-compiling on Unix-like systems + Using HP's ANSI C++ compiler (aCC) + Making new tarballs + Testing PCRE + Character tables + File manifest The PCRE APIs ------------- -PCRE is written in C, and it has its own API. The distribution now includes a -set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page -for details). - -Also included are a set of C wrapper functions that are based on the POSIX -API. These end up in the library called libpcreposix. Note that this just -provides a POSIX calling interface to PCRE: the regular expressions themselves -still follow Perl syntax and semantics. The header file for the POSIX-style -functions is called pcreposix.h. The official POSIX name is regex.h, but I -didn't want to risk possible problems with existing files of that name by -distributing it that way. To use it with an existing program that uses the -POSIX API, it will have to be renamed or pointed at by a link. +PCRE is written in C, and it has its own API. The distribution also includes a +set of C++ wrapper functions (see the pcrecpp man page for details), courtesy +of Google Inc. + +In addition, there is a set of C wrapper functions that are based on the POSIX +regular expression API (see the pcreposix man page). These end up in the +library called libpcreposix. Note that this just provides a POSIX calling +interface to PCRE; the regular expressions themselves still follow Perl syntax +and semantics. The POSIX API is restricted, and does not give full access to +all of PCRE's facilities. + +The header file for the POSIX-style functions is called pcreposix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE with +an existing program that uses the POSIX API, pcreposix.h will have to be +renamed or pointed at by a link. If you are using the POSIX interface to PCRE and there is already a POSIX regex -library installed on your system, you must take care when linking programs to +library installed on your system, as well as worrying about the regex.h header +file (as mentioned above), you must also take care when linking programs to ensure that they link with PCRE's libpcreposix library. Otherwise they may pick -up the "real" POSIX functions of the same name. +up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE with the addition of +-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. Documentation for PCRE ---------------------- -If you install PCRE in the normal way, you will end up with an installed set of -man pages whose names all start with "pcre". The one that is just called "pcre" -lists all the others. In addition to these man pages, the PCRE documentation is -supplied in two other forms; however, as there is no standard place to install -them, they are left in the doc directory of the unpacked source distribution. -These forms are: - - 1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. The - first of these is a concatenation of the text forms of all the section 3 - man pages except those that summarize individual functions. The other two - are the text forms of the section 1 man pages for the pcregrep and - pcretest commands. Text forms are provided for ease of scanning with text - editors or similar tools. - - 2. A subdirectory called doc/html contains all the documentation in HTML - form, hyperlinked in various ways, and rooted in a file called - doc/index.html. +If you install PCRE in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre". The one that is just +called "pcre" lists all the others. In addition to these man pages, the PCRE +documentation is supplied in two other forms: + + 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and + doc/pcretest.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except + those that summarize individual functions. The other two are the text + forms of the section 1 man pages for the pcregrep and pcretest commands. + These text forms are provided for ease of scanning with text editors or + similar tools. They are installed in <prefix>/share/doc/pcre, where + <prefix> is the installation prefix (defaulting to /usr/local). + + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in <prefix>/share/doc/pcre/html. + +Users of PCRE have contributed files containing the documentation for various +releases in CHM format. These can be found in the Contrib directory of the FTP +site (see next section). Contributions by users of PCRE @@ -59,27 +97,48 @@ ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib -where there is also a README file giving brief descriptions of what they are. -Several of them provide support for compiling PCRE on various flavours of -Windows systems (I myself do not use Windows). Some are complete in themselves; -others are pointers to URLs containing relevant files. +There is a README file giving brief descriptions of what they are. Some are +complete in themselves; others are pointers to URLs containing relevant files. +Some of this material is likely to be well out-of-date. Several of the earlier +contributions provided support for compiling PCRE on various flavours of +Windows (I myself do not use Windows). Nowadays there is more Windows support +in the standard distribution, so these contibutions have been archived. + +Building PCRE on non-Unix systems +--------------------------------- -Building PCRE on a Unix-like system ------------------------------------ +For a non-Unix system, please read the comments in the file NON-UNIX-USE, +though if your system supports the use of "configure" and "make" you may be +able to build PCRE in the same way as for Unix-like systems. PCRE can also be +configured in many platform environments using the GUI facility of CMake's +CMakeSetup. It creates Makefiles, solution files, etc. + +PCRE has been compiled on many different operating systems. It should be +straightforward to build PCRE on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE on Unix-like systems +---------------------------------- If you are using HP's ANSI C++ compiler (aCC), please see the special note in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. +The following instructions assume the use of the widely used "configure, make, +make install" process. There is also support for CMake in the PCRE +distribution; there are some comments about using CMake in the NON-UNIX-USE +file, though it can also be used in Unix-like systems. + To build PCRE on a Unix-like system, first run the "configure" command from the PCRE distribution directory, with your current directory set to the directory where you want the files to be created. This command is a standard GNU "autoconf" configuration script, for which generic instructions are supplied in -INSTALL. +the file INSTALL. Most commonly, people build PCRE within its own distribution directory, and in -this case, on many systems, just running "./configure" is sufficient, but the -usual methods of changing standard defaults are available. For example: +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local @@ -103,13 +162,16 @@ . If you want to suppress the building of the C++ wrapper library, you can add --disable-cpp to the "configure" command. Otherwise, when "configure" is run, - will try to find a C++ compiler and C++ header files, and if it succeeds, it - will try to build the C++ wrapper. + it will try to find a C++ compiler and C++ header files, and if it succeeds, + it will try to build the C++ wrapper. -. If you want to make use of the support for UTF-8 character strings in PCRE, - you must add --enable-utf8 to the "configure" command. Without it, the code - for handling UTF-8 is not included in the library. (Even when included, it - still has to be enabled by an option at run time.) +. If you want to make use of the support for UTF-8 Unicode character strings in + PCRE, you must add --enable-utf8 to the "configure" command. Without it, the + code for handling UTF-8 is not included in the library. Even when included, + it still has to be enabled by an option at run time. When PCRE is compiled + with this option, its input can only either be ASCII or UTF-8, even when + running on EBCDIC platforms. It is not possible to use both --enable-utf8 and + --enable-ebcdic at the same time. . If, in addition to support for UTF-8 character strings, you want to include support for the \P, \p, and \X sequences that recognize Unicode character @@ -118,17 +180,31 @@ property table); only the basic two-letter properties such as Lu are supported. -. You can build PCRE to recognize either CR or LF or the sequence CRLF as - indicating the end of a line. Whatever you specify at build time is the - default; the caller of PCRE can change the selection at run time. The default - newline indicator is a single LF character (the Unix standard). You can - specify the default newline indicator by adding --newline-is-cr or - --newline-is-lf or --newline-is-crlf to the "configure" command, - respectively. +. You can build PCRE to recognize either CR or LF or the sequence CRLF or any + of the preceding, or any of the Unicode newline sequences as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf + or --enable-newline-is-crlf or --enable-newline-is-anycrlf or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. + +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE considers to + be the end of a line (see above). However, the caller of PCRE can restrict \R + to match only CR, LF, or CRLF. You can make this the default by adding + --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). . When called via the POSIX interface, PCRE uses malloc() to get additional storage for processing capturing parentheses if there are more than 10 of - them. You can increase this threshold by setting, for example, + them in a pattern. You can increase this threshold by setting, for example, --with-posix-malloc-threshold=20 @@ -141,8 +217,8 @@ --with-match-limit=500000 on the "configure" command. This is just the default; individual calls to - pcre_exec() can supply their own value. There is discussion on the pcreapi - man page. + pcre_exec() can supply their own value. There is more discussion on the + pcreapi man page. . There is a separate counter that limits the depth of recursive function calls during a matching process. This also has a default of ten million, which is @@ -157,37 +233,92 @@ . The default maximum compiled pattern size is around 64K. You can increase this by adding --with-link-size=3 to the "configure" command. You can increase it even more by setting --with-link-size=4, but this is unlikely - ever to be necessary. If you build PCRE with an increased link size, test 2 - (and 5 if you are using UTF-8) will fail. Part of the output of these tests - is a representation of the compiled pattern, and this changes with the link - size. + ever to be necessary. Increasing the internal link size will reduce + performance. . You can build PCRE so that its internal match() function that is called from - pcre_exec() does not call itself recursively. Instead, it uses blocks of data - from the heap via special functions pcre_stack_malloc() and pcre_stack_free() - to save data that would otherwise be saved on the stack. To build PCRE like - this, use + pcre_exec() does not call itself recursively. Instead, it uses memory blocks + obtained from the heap via the special functions pcre_stack_malloc() and + pcre_stack_free() to save data that would otherwise be saved on the stack. To + build PCRE like this, use --disable-stack-for-recursion on the "configure" command. PCRE runs more slowly in this mode, but it may be necessary in environments with limited stack sizes. This applies only to the pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not - use deeply nested recursion. + use deeply nested recursion. There is a discussion about stack sizes in the + pcrestack man page. + +. For speed, PCRE uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre_chartables.c. If you do + not specify this option, pcre_chartables.c is created as a copy of + pcre_chartables.c.dist. See "Character tables" below for further information. + +. It is possible to compile PCRE for use on systems that use EBCDIC as their + character code (as opposed to ASCII) by specifying + + --enable-ebcdic + + This automatically implies --enable-rebuild-chartables (see above). However, + when PCRE is built this way, it always operates in EBCDIC. It cannot support + both EBCDIC and UTF-8. + +. It is possible to compile pcregrep to use libz and/or libbz2, in order to + read .gz and .bz2 files (respectively), by specifying one or both of -The "configure" script builds eight files for the basic C library: + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. It is possible to compile pcretest so that it links with the libreadline + library, by specifying + + --enable-pcretest-libreadline + + If this is done, when pcretest's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + + Setting this option causes the -lreadline option to be added to the pcretest + build. In many operating environments with a sytem-installed readline + library this is sufficient. However, in some environments (e.g. if an + unmodified distribution version of readline is in use), it may be necessary + to specify something like LIBS="-lncurses" as well. This is because, to quote + the readline INSTALL, "Readline uses the termcap functions, but does not link + with the termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." If you get error + messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto, + this is the problem, and linking with the ncurses library should fix it. + +The "configure" script builds the following files for the basic C library: . Makefile is the makefile that builds the library . config.h contains build-time configuration options for the library +. pcre.h is the public PCRE header file . pcre-config is a script that shows the settings of "configure" options . libpcre.pc is data for the pkg-config command . libtool is a script that builds shared and/or static libraries -. RunTest is a script for running tests on the library +. RunTest is a script for running tests on the basic C library . RunGrepTest is a script for running tests on the pcregrep command -In addition, if a C++ compiler is found, the following are also built: +Versions of config.h and pcre.h are distributed in the PCRE tarballs under +the names config.h.generic and pcre.h.generic. These are provided for the +benefit of those who have to built PCRE without the benefit of "configure". If +you use "configure", the .generic versions are not used. -. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper +If a C++ compiler is found, the following files are also built: + +. libpcrecpp.pc is data for the pkg-config command +. pcrecpparg.h is a header file for programs that call PCRE via the C++ wrapper . pcre_stringpiece.h is the header for the C++ "stringpiece" functions The "configure" script also creates config.status, which is an executable @@ -196,17 +327,61 @@ Once "configure" has run, you can run "make". It builds two libraries, called libpcre and libpcreposix, a test program called pcretest, and the pcregrep -command. If a C++ compiler was found on your system, it also builds the C++ +command. If a C++ compiler was found on your system, "make" also builds the C++ wrapper library, which is called libpcrecpp, and some test programs called pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. +Building the C++ wrapper can be disabled by adding --disable-cpp to the +"configure" command. -The command "make test" runs all the appropriate tests. Details of the PCRE -tests are given in a separate section of this document, below. +The command "make check" runs all the appropriate tests. Details of the PCRE +tests are given below in a separate section of this document. -You can use "make install" to copy the libraries, the public header files -pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if -the C++ wrapper was built), and the man pages to appropriate live directories -on your system, in the normal way. +You can use "make install" to install PCRE into live directories on your +system. The following are installed (file names are all relative to the +<prefix> that is set when "configure" is run): + + Commands (bin): + pcretest + pcregrep + pcre-config + + Libraries (lib): + libpcre + libpcreposix + libpcrecpp (if C++ support is enabled) + + Configuration information (lib/pkgconfig): + libpcre.pc + libpcrecpp.pc (if C++ support is enabled) + + Header files (include): + pcre.h + pcreposix.h + pcre_scanner.h ) + pcre_stringpiece.h ) if C++ support is enabled + pcrecpp.h ) + pcrecpparg.h ) + + Man pages (share/man/man{1,3}): + pcregrep.1 + pcretest.1 + pcre.3 + pcre*.3 (lots more pages, all starting "pcre") + + HTML documentation (share/doc/pcre/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre.txt (a concatenation of the man(3) pages) + pcretest.txt the pcretest man page + pcregrep.txt the pcregrep man page If you want to remove PCRE from your system, you can run "make uninstall". This removes all the files that "make install" installed. However, it does not @@ -216,9 +391,8 @@ Retrieving configuration information on Unix-like systems --------------------------------------------------------- -Running "make install" also installs the command pcre-config, which can be used -to recall information about the PCRE configuration and installation. For -example: +Running "make install" installs the command pcre-config, which can be used to +recall information about the PCRE configuration and installation. For example: pcre-config --version @@ -237,7 +411,7 @@ pkg-config --cflags pcre The data is held in *.pc files that are installed in a directory called -pkgconfig. +<prefix>/lib/pkgconfig. Shared libraries on Unix-like systems @@ -254,7 +428,7 @@ libraries (by means of wrapper scripts in the case of shared libraries). When you use "make install" to install shared libraries, pcregrep and pcretest are automatically re-built to use the newly installed shared libraries before being -installed themselves. However, the versions left in the source directory still +installed themselves. However, the versions left in the build directory still use the uninstalled libraries. To build PCRE using static libraries only you must use --disable-shared when @@ -266,25 +440,33 @@ build only shared libraries. -Cross-compiling on a Unix-like system -------------------------------------- +Cross-compiling on Unix-like systems +------------------------------------ You can specify CC and CFLAGS in the normal way to the "configure" command, in -order to cross-compile PCRE for some other host. However, during the building -process, the dftables.c source file is compiled *and run* on the local host, in -order to generate the default character tables (the chartables.c file). It -therefore needs to be compiled with the local compiler, not the cross compiler. -You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD; -there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper) -when calling the "configure" command. If they are not specified, they default -to the values of CC and CFLAGS. +order to cross-compile PCRE for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre_chartables.c is created +by making a copy of pcre_chartables.c.dist, which is a default set of tables +that assumes ASCII code. Cross-compiling with the default tables should not be +a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and +run it on the local host to make a new version of pcre_chartables.c.dist. +Then when you cross-compile PCRE this new version of the tables will be used. Using HP's ANSI C++ compiler (aCC) ---------------------------------- -Unless C++ support is disabled by specifiying the "--disable-cpp" option of the -"configure" script, you *must* include the "-AA" option in the CXXFLAGS +Unless C++ support is disabled by specifying the "--disable-cpp" option of the +"configure" script, you must include the "-AA" option in the CXXFLAGS environment variable in order for the C++ components to compile correctly. Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby @@ -296,49 +478,48 @@ CXXLDFLAGS="-lstd_v2 -lCsup_v2" -Building on non-Unix systems ----------------------------- +Making new tarballs +------------------- -For a non-Unix system, read the comments in the file NON-UNIX-USE, though if -the system supports the use of "configure" and "make" you may be able to build -PCRE in the same way as for Unix systems. - -PCRE has been compiled on Windows systems and on Macintoshes, but I don't know -the details because I don't use those systems. It should be straightforward to -build PCRE on any system that has a Standard C compiler, because it uses only -Standard C functions. +The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. + +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. Testing PCRE ------------ -To test PCRE on a Unix system, run the RunTest script that is created by the -configuring process. There is also a script called RunGrepTest that tests the -options of the pcregrep command. If the C++ wrapper library is build, three -test programs called pcrecpp_unittest, pcre_scanner_unittest, and -pcre_stringpiece_unittest are provided. - -Both the scripts and all the program tests are run if you obey "make runtest", -"make check", or "make test". For other systems, see the instructions in -NON-UNIX-USE. +To test the basic PCRE library on a Unix system, run the RunTest script that is +created by the configuring process. There is also a script called RunGrepTest +that tests the options of the pcregrep command. If the C++ wrapper library is +built, three test programs called pcrecpp_unittest, pcre_scanner_unittest, and +pcre_stringpiece_unittest are also built. + +Both the scripts and all the program tests are run if you obey "make check" or +"make test". For other systems, see the instructions in NON-UNIX-USE. The RunTest script runs the pcretest test program (which is documented in its -own man page) on each of the testinput files (in the testdata directory) in +own man page) on each of the testinput files in the testdata directory in turn, and compares the output with the contents of the corresponding testoutput -file. A file called testtry is used to hold the main output from pcretest +files. A file called testtry is used to hold the main output from pcretest (testsavedregex is also used as a working file). To run pcretest on just one of the test files, give its number as an argument to RunTest, for example: RunTest 2 -The first file can also be fed directly into the perltest script to check that -Perl gives the same results. The only difference you should see is in the first -few lines, where the Perl version is given instead of the PCRE version. +The first test file can also be fed directly into the perltest.pl script to +check that Perl gives the same results. The only difference you should see is +in the first few lines, where the Perl version is given instead of the PCRE +version. The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error detection, and run-time flags that are specific to PCRE, as well as the POSIX -wrapper API. It also uses the debugging flag to check some of the internals of +wrapper API. It also uses the debugging flags to check some of the internals of pcre_compile(). If you build PCRE with a locale setting that is not the standard C locale, the @@ -364,6 +545,12 @@ in the comparison output, it means that locale is not available on your system, despite being listed by "locale". This does not mean that PCRE is broken. +[If you are trying to run this test on Windows, you may be able to get it to +work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use +RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses +Windows versions of test 2. More info on using RunTest.bat is included in the +document entitled NON-UNIX-USE.] + The fourth test checks the UTF-8 support. It is not run automatically unless PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when running "configure". This file can be also fed directly to the perltest script, @@ -373,8 +560,8 @@ The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 features of PCRE that are not relevant to Perl. -The sixth and test checks the support for Unicode character properties. It it -not run automatically unless PCRE is built with Unicode property support. To to +The sixth test checks the support for Unicode character properties. It it not +run automatically unless PCRE is built with Unicode property support. To to this you must set --enable-unicode-properties when running "configure". The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative @@ -386,27 +573,42 @@ Character tables ---------------- -PCRE uses four tables for manipulating and identifying characters whose values -are less than 256. The final argument of the pcre_compile() function is a -pointer to a block of memory containing the concatenated tables. A call to -pcre_maketables() can be used to generate a set of tables in the current -locale. If the final argument for pcre_compile() is passed as NULL, a set of -default tables that is built into the binary is used. - -The source file called chartables.c contains the default set of tables. This is -not supplied in the distribution, but is built by the program dftables -(compiled from dftables.c), which uses the ANSI C character handling functions -such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table -sources. This means that the default C locale which is set for your system will -control the contents of these default tables. You can change the default tables -by editing chartables.c and then re-building PCRE. If you do this, you should -probably also edit Makefile to ensure that the file doesn't ever get -re-generated. +For speed, PCRE uses four tables for manipulating and identifying characters +whose code point values are less than 256. The final argument of the +pcre_compile() function is a pointer to a block of memory containing the +concatenated tables. A call to pcre_maketables() can be used to generate a set +of tables in the current locale. If the final argument for pcre_compile() is +passed as NULL, a set of default tables that is built into the binary is used. + +The source file called pcre_chartables.c contains the default set of tables. By +default, this is created as a copy of pcre_chartables.c.dist, which contains +tables for ASCII coding. However, if --enable-rebuild-chartables is specified +for ./configure, a different version of pcre_chartables.c is built by the +program dftables (compiled from dftables.c), which uses the ANSI C character +handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to +build the table sources. This means that the default C locale which is set for +your system will control the contents of these default tables. You can change +the default tables by editing pcre_chartables.c and then re-building PCRE. If +you do this, you should take care to ensure that the file does not get +automatically re-generated. The best way to do this is to move +pcre_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre_chartables.c.special The first two 256-byte tables provide lower casing and case flipping functions, respectively. The next table consists of three 32-byte bit maps which identify digits, "word" characters, and white space, respectively. These are used when -building 32-byte bit maps that represent character classes. +building 32-byte bit maps that represent character classes for code points less +than 256. The final 256-byte table has bits indicating various character types, as follows: @@ -422,107 +624,144 @@ will cause PCRE to malfunction. -Manifest --------- +File manifest +------------- The distribution should contain the following files: -(A) The actual source files of the PCRE library functions and their - headers: +(A) Source files of the PCRE library functions and their headers: - dftables.c auxiliary program for building chartables.c + dftables.c auxiliary program for building pcre_chartables.c + when --enable-rebuild-chartables is specified - pcreposix.c ) - pcre_compile.c ) - pcre_config.c ) - pcre_dfa_exec.c ) - pcre_exec.c ) - pcre_fullinfo.c ) - pcre_get.c ) sources for the functions in the library, - pcre_globals.c ) and some internal functions that they use - pcre_info.c ) - pcre_maketables.c ) - pcre_ord2utf8.c ) - pcre_refcount.c ) - pcre_study.c ) - pcre_tables.c ) - pcre_try_flipped.c ) - pcre_ucp_searchfuncs.c) - pcre_valid_utf8.c ) - pcre_version.c ) - pcre_xclass.c ) - ucptable.c ) - - pcre_printint.src ) debugging function that is #included in pcretest, and - ) can also be #included in pcre_compile() - - pcre.h the public PCRE header file - pcreposix.h header for the external POSIX wrapper API - pcre_internal.h header for internal use - ucp.h ) headers concerned with - ucpinternal.h ) Unicode property handling - config.in template for config.h, which is built by configure - - pcrecpp.h the header file for the C++ wrapper - pcrecpparg.h.in "source" for another C++ header file - pcrecpp.cc ) - pcre_scanner.cc ) source for the C++ wrapper library - - pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the - C++ stringpiece functions - pcre_stringpiece.cc source for the C++ stringpiece functions - -(B) Auxiliary files: - - AUTHORS information about the author of PCRE - ChangeLog log of changes to the code - INSTALL generic installation instructions - LICENCE conditions for the use of PCRE - COPYING the same, using GNU's standard name - Makefile.in template for Unix Makefile, which is built by configure - NEWS important changes in this release - NON-UNIX-USE notes on building PCRE on non-Unix systems - README this file - RunTest.in template for a Unix shell script for running tests - RunGrepTest.in template for a Unix shell script for pcregrep tests - config.guess ) files used by libtool, - config.sub ) used only when building a shared library - config.h.in "source" for the config.h header file - configure a configuring shell script (built by autoconf) - configure.ac the autoconf input used to build configure - doc/Tech.Notes notes on the encoding - doc/*.3 man page sources for the PCRE functions - doc/*.1 man page sources for pcregrep and pcretest - doc/html/* HTML documentation - doc/pcre.txt plain text version of the man pages - doc/pcretest.txt plain text documentation of test program - doc/perltest.txt plain text documentation of Perl test program - install-sh a shell script for installing files - libpcre.pc.in "source" for libpcre.pc for pkg-config - ltmain.sh file used to build a libtool script - mkinstalldirs script for making install directories - pcretest.c comprehensive test program - pcredemo.c simple demonstration of coding calls to PCRE - perltest Perl test program - pcregrep.c source of a grep utility that uses PCRE - pcre-config.in source of script which retains PCRE information - pcrecpp_unittest.c ) - pcre_scanner_unittest.c ) test programs for the C++ wrapper - pcre_stringpiece_unittest.c ) - testdata/testinput* test data for main library tests - testdata/testoutput* expected test results - testdata/grep* input and output for pcregrep tests + pcre_chartables.c.dist a default set of character tables that assume ASCII + coding; used, unless --enable-rebuild-chartables is + specified, by copying to pcre_chartables.c + + pcreposix.c ) + pcre_compile.c ) + pcre_config.c ) + pcre_dfa_exec.c ) + pcre_exec.c ) + pcre_fullinfo.c ) + pcre_get.c ) sources for the functions in the library, + pcre_globals.c ) and some internal functions that they use + pcre_info.c ) + pcre_maketables.c ) + pcre_newline.c ) + pcre_ord2utf8.c ) + pcre_refcount.c ) + pcre_study.c ) + pcre_tables.c ) + pcre_try_flipped.c ) + pcre_ucd.c ) + pcre_valid_utf8.c ) + pcre_version.c ) + pcre_xclass.c ) + pcre_printint.src ) debugging function that is #included in pcretest, + ) and can also be #included in pcre_compile() + pcre.h.in template for pcre.h when built by "configure" + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + ucp.h header for Unicode property handling + + config.h.in template for config.h, which is built by "configure" + + pcrecpp.h public header file for the C++ wrapper + pcrecpparg.h.in template for another C++ header file + pcre_scanner.h public header file for C++ scanner functions + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library + + pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions + +(B) Source files for programs that use PCRE: + + pcredemo.c simple demonstration of coding calls to PCRE + pcregrep.c source of a grep utility that uses PCRE + pcretest.c comprehensive test program + +(C) Auxiliary files: + + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-UNIX-USE notes on building PCRE on non-Unix systems + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcregrep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for the PCRE functions + doc/*.1 man page sources for pcregrep and pcretest + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre.pc.in template for libpcre.pc for pkg-config + libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.pl Perl test program + pcre-config.in source of script which retains PCRE information + pcrecpp_unittest.cc ) + pcre_scanner_unittest.cc ) test programs for the C++ wrapper + pcre_stringpiece_unittest.cc ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests + +(D) Auxiliary files for cmake support + + cmake/COPYING-CMAKE-SCRIPTS + cmake/FindPackageHandleStandardArgs.cmake + cmake/FindReadline.cmake + CMakeLists.txt + config-cmake.h.in -(C) Auxiliary files for Win32 DLL +(E) Auxiliary files for VPASCAL - libpcre.def - libpcreposix.def + makevp.bat + makevp_c.txt + makevp_l.txt + pcregexp.pas -(D) Auxiliary file for VPASCAL +(F) Auxiliary files for building PCRE "by hand" - makevp.bat + pcre.h.generic ) a version of the public PCRE header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +(F) Miscellaneous + + RunTest.bat a script for running tests under Windows Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -June 2006 +Last updated: 21 March 2009 Added: freeswitch/trunk/libs/pcre/RunTest.bat ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/RunTest.bat Mon Jun 8 18:51:30 2009 @@ -0,0 +1,39 @@ +@rem This file was contributed by Ralf Junker, and touched up by +@rem Daniel Richard G. Test 10 added by Philip H. +@rem Philip H also changed test 3 to use "wintest" files. +@rem +@rem MS Windows batch file to run pcretest on testfiles with the correct +@rem options. +@rem +@rem Output is written to a newly created subfolder named "testdata". + +setlocal + +if [%srcdir%]==[] set srcdir=. +if [%pcretest%]==[] set pcretest=pcretest + +if not exist testout md testout + +%pcretest% -q %srcdir%\testdata\testinput1 > testout\testoutput1 +%pcretest% -q %srcdir%\testdata\testinput2 > testout\testoutput2 +@rem %pcretest% -q %srcdir%\testdata\testinput3 > testout\testoutput3 +%pcretest% -q %srcdir%\testdata\wintestinput3 > testout\wintestoutput3 +%pcretest% -q %srcdir%\testdata\testinput4 > testout\testoutput4 +%pcretest% -q %srcdir%\testdata\testinput5 > testout\testoutput5 +%pcretest% -q %srcdir%\testdata\testinput6 > testout\testoutput6 +%pcretest% -q -dfa %srcdir%\testdata\testinput7 > testout\testoutput7 +%pcretest% -q -dfa %srcdir%\testdata\testinput8 > testout\testoutput8 +%pcretest% -q -dfa %srcdir%\testdata\testinput9 > testout\testoutput9 +%pcretest% -q %srcdir%\testdata\testinput10 > testout\testoutput10 + +fc /n %srcdir%\testdata\testoutput1 testout\testoutput1 +fc /n %srcdir%\testdata\testoutput2 testout\testoutput2 +rem fc /n %srcdir%\testdata\testoutput3 testout\testoutput3 +fc /n %srcdir%\testdata\wintestoutput3 testout\wintestoutput3 +fc /n %srcdir%\testdata\testoutput4 testout\testoutput4 +fc /n %srcdir%\testdata\testoutput5 testout\testoutput5 +fc /n %srcdir%\testdata\testoutput6 testout\testoutput6 +fc /n %srcdir%\testdata\testoutput7 testout\testoutput7 +fc /n %srcdir%\testdata\testoutput8 testout\testoutput8 +fc /n %srcdir%\testdata\testoutput9 testout\testoutput9 +fc /n %srcdir%\testdata\testoutput10 testout\testoutput10 Added: freeswitch/trunk/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS Mon Jun 8 18:51:30 2009 @@ -0,0 +1,22 @@ +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + +1. Redistributions of source code must retain the copyright + notice, this list of conditions and the following disclaimer. +2. Redistributions in binary form must reproduce the copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. +3. The name of the author may not be used to endorse or promote products + derived from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR +IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES +OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. +IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, +INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT +NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF +THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. Added: freeswitch/trunk/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake Mon Jun 8 18:51:30 2009 @@ -0,0 +1,58 @@ +# FIND_PACKAGE_HANDLE_STANDARD_ARGS(NAME (DEFAULT_MSG|"Custom failure message") VAR1 ... ) +# This macro is intended to be used in FindXXX.cmake modules files. +# It handles the REQUIRED and QUIET argument to FIND_PACKAGE() and +# it also sets the <UPPERCASED_NAME>_FOUND variable. +# The package is found if all variables listed are TRUE. +# Example: +# +# FIND_PACKAGE_HANDLE_STANDARD_ARGS(LibXml2 DEFAULT_MSG LIBXML2_LIBRARIES LIBXML2_INCLUDE_DIR) +# +# LibXml2 is considered to be found, if both LIBXML2_LIBRARIES and +# LIBXML2_INCLUDE_DIR are valid. Then also LIBXML2_FOUND is set to TRUE. +# If it is not found and REQUIRED was used, it fails with FATAL_ERROR, +# independent whether QUIET was used or not. +# If it is found, the location is reported using the VAR1 argument, so +# here a message "Found LibXml2: /usr/lib/libxml2.so" will be printed out. +# If the second argument is DEFAULT_MSG, the message in the failure case will +# be "Could NOT find LibXml2", if you don't like this message you can specify +# your own custom failure message there. + +MACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS _NAME _FAIL_MSG _VAR1 ) + + IF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") + IF (${_NAME}_FIND_REQUIRED) + SET(_FAIL_MESSAGE "Could not find REQUIRED package ${_NAME}") + ELSE (${_NAME}_FIND_REQUIRED) + SET(_FAIL_MESSAGE "Could not find OPTIONAL package ${_NAME}") + ENDIF (${_NAME}_FIND_REQUIRED) + ELSE("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") + SET(_FAIL_MESSAGE "${_FAIL_MSG}") + ENDIF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") + + STRING(TOUPPER ${_NAME} _NAME_UPPER) + + SET(${_NAME_UPPER}_FOUND TRUE) + IF(NOT ${_VAR1}) + SET(${_NAME_UPPER}_FOUND FALSE) + ENDIF(NOT ${_VAR1}) + + FOREACH(_CURRENT_VAR ${ARGN}) + IF(NOT ${_CURRENT_VAR}) + SET(${_NAME_UPPER}_FOUND FALSE) + ENDIF(NOT ${_CURRENT_VAR}) + ENDFOREACH(_CURRENT_VAR) + + IF (${_NAME_UPPER}_FOUND) + IF (NOT ${_NAME}_FIND_QUIETLY) + MESSAGE(STATUS "Found ${_NAME}: ${${_VAR1}}") + ENDIF (NOT ${_NAME}_FIND_QUIETLY) + ELSE (${_NAME_UPPER}_FOUND) + IF (${_NAME}_FIND_REQUIRED) + MESSAGE(FATAL_ERROR "${_FAIL_MESSAGE}") + ELSE (${_NAME}_FIND_REQUIRED) + IF (NOT ${_NAME}_FIND_QUIETLY) + MESSAGE(STATUS "${_FAIL_MESSAGE}") + ENDIF (NOT ${_NAME}_FIND_QUIETLY) + ENDIF (${_NAME}_FIND_REQUIRED) + ENDIF (${_NAME_UPPER}_FOUND) +ENDMACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS) Added: freeswitch/trunk/libs/pcre/cmake/FindReadline.cmake ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/cmake/FindReadline.cmake Mon Jun 8 18:51:30 2009 @@ -0,0 +1,29 @@ +# from http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/FindReadline.cmake +# http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/COPYING-CMAKE-SCRIPTS +# --> BSD licensed +# +# GNU Readline library finder +if(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) + set(READLINE_FOUND TRUE) +else(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) + FIND_PATH(READLINE_INCLUDE_DIR readline/readline.h + /usr/include/readline + ) + +# 2008-04-22 The next clause used to read like this: +# +# FIND_LIBRARY(READLINE_LIBRARY NAMES readline) +# FIND_LIBRARY(NCURSES_LIBRARY NAMES ncurses ) +# include(FindPackageHandleStandardArgs) +# FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG NCURSES_LIBRARY READLINE_INCLUDE_DIR READLINE_LIBRARY ) +# +# I was advised to modify it such that it will find an ncurses library if +# required, but not if one was explicitly given, that is, it allows the +# default to be overridden. PH + + FIND_LIBRARY(READLINE_LIBRARY NAMES readline) + include(FindPackageHandleStandardArgs) + FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG READLINE_INCLUDE_DIR READLINE_LIBRARY ) + + MARK_AS_ADVANCED(READLINE_INCLUDE_DIR READLINE_LIBRARY) +endif(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) Added: freeswitch/trunk/libs/pcre/config-cmake.h.in ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/config-cmake.h.in Mon Jun 8 18:51:30 2009 @@ -0,0 +1,44 @@ +/* config.h for CMake builds */ + +#cmakedefine HAVE_DIRENT_H 1 +#cmakedefine HAVE_SYS_STAT_H 1 +#cmakedefine HAVE_SYS_TYPES_H 1 +#cmakedefine HAVE_UNISTD_H 1 +#cmakedefine HAVE_WINDOWS_H 1 + +#cmakedefine HAVE_TYPE_TRAITS_H 1 +#cmakedefine HAVE_BITS_TYPE_TRAITS_H 1 + +#cmakedefine HAVE_BCOPY 1 +#cmakedefine HAVE_MEMMOVE 1 +#cmakedefine HAVE_STRERROR 1 +#cmakedefine HAVE_STRTOLL 1 +#cmakedefine HAVE_STRTOQ 1 +#cmakedefine HAVE__STRTOI64 1 + +#cmakedefine PCRE_STATIC 1 + +#cmakedefine SUPPORT_UTF8 1 +#cmakedefine SUPPORT_UCP 1 +#cmakedefine EBCDIC 1 +#cmakedefine BSR_ANYCRLF 1 +#cmakedefine NO_RECURSE 1 + +#cmakedefine HAVE_LONG_LONG 1 +#cmakedefine HAVE_UNSIGNED_LONG_LONG 1 + +#cmakedefine SUPPORT_LIBBZ2 1 +#cmakedefine SUPPORT_LIBZ 1 +#cmakedefine SUPPORT_LIBREADLINE 1 + +#define NEWLINE @NEWLINE@ +#define POSIX_MALLOC_THRESHOLD @PCRE_POSIX_MALLOC_THRESHOLD@ +#define LINK_SIZE @PCRE_LINK_SIZE@ +#define MATCH_LIMIT @PCRE_MATCH_LIMIT@ +#define MATCH_LIMIT_RECURSION @PCRE_MATCH_LIMIT_RECURSION@ + + +#define MAX_NAME_SIZE 32 +#define MAX_NAME_COUNT 10000 + +/* end config.h for CMake builds */ Added: freeswitch/trunk/libs/pcre/config.h.generic ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/config.h.generic Mon Jun 8 18:51:30 2009 @@ -0,0 +1,313 @@ +/* config.h. Generated from config.h.in by configure. */ +/* config.h.in. Generated from configure.ac by autoheader. */ + + +/* On Unix-like systems config.h.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to +all of your compile commands, so that config.h is included at the start of +every source. + +Alternatively, you can avoid editing by using -D on the compiler command line +to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */ + +/* By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- time + default can be overridden by the user of PCRE at runtime. On systems that + support it, "configure" can be used to override the default. */ +/* #undef BSR_ANYCRLF */ + +/* If you are compiling for a system that uses EBCDIC instead of ASCII + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic. PCRE will then assume + that all input strings are in EBCDIC. If you do not define this macro, PCRE + will assume input strings are ASCII or UTF-8 Unicode. It is not possible to + build a version of PCRE that supports both EBCDIC and UTF-8. */ +/* #undef EBCDIC */ + +/* Define to 1 if you have the `bcopy' function. */ +#ifndef HAVE_BCOPY +#define HAVE_BCOPY 1 +#endif + +/* Define to 1 if you have the <bits/type_traits.h> header file. */ +/* #undef HAVE_BITS_TYPE_TRAITS_H */ + +/* Define to 1 if you have the <bzlib.h> header file. */ +#ifndef HAVE_BZLIB_H +#define HAVE_BZLIB_H 1 +#endif + +/* Define to 1 if you have the <dirent.h> header file. */ +#ifndef HAVE_DIRENT_H +#define HAVE_DIRENT_H 1 +#endif + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#ifndef HAVE_DLFCN_H +#define HAVE_DLFCN_H 1 +#endif + +/* Define to 1 if you have the <inttypes.h> header file. */ +#ifndef HAVE_INTTYPES_H +#define HAVE_INTTYPES_H 1 +#endif + +/* Define to 1 if you have the <limits.h> header file. */ +#ifndef HAVE_LIMITS_H +#define HAVE_LIMITS_H 1 +#endif + +/* Define to 1 if the system has the type `long long'. */ +#ifndef HAVE_LONG_LONG +#define HAVE_LONG_LONG 1 +#endif + +/* Define to 1 if you have the `memmove' function. */ +#ifndef HAVE_MEMMOVE +#define HAVE_MEMMOVE 1 +#endif + +/* Define to 1 if you have the <memory.h> header file. */ +#ifndef HAVE_MEMORY_H +#define HAVE_MEMORY_H 1 +#endif + +/* Define to 1 if you have the <readline/history.h> header file. */ +#ifndef HAVE_READLINE_HISTORY_H +#define HAVE_READLINE_HISTORY_H 1 +#endif + +/* Define to 1 if you have the <readline/readline.h> header file. */ +#ifndef HAVE_READLINE_READLINE_H +#define HAVE_READLINE_READLINE_H 1 +#endif + +/* Define to 1 if you have the <stdint.h> header file. */ +#ifndef HAVE_STDINT_H +#define HAVE_STDINT_H 1 +#endif + +/* Define to 1 if you have the <stdlib.h> header file. */ +#ifndef HAVE_STDLIB_H +#define HAVE_STDLIB_H 1 +#endif + +/* Define to 1 if you have the `strerror' function. */ +#ifndef HAVE_STRERROR +#define HAVE_STRERROR 1 +#endif + +/* Define to 1 if you have the <string> header file. */ +#ifndef HAVE_STRING +#define HAVE_STRING 1 +#endif + +/* Define to 1 if you have the <strings.h> header file. */ +#ifndef HAVE_STRINGS_H +#define HAVE_STRINGS_H 1 +#endif + +/* Define to 1 if you have the <string.h> header file. */ +#ifndef HAVE_STRING_H +#define HAVE_STRING_H 1 +#endif + +/* Define to 1 if you have the `strtoll' function. */ +/* #undef HAVE_STRTOLL */ + +/* Define to 1 if you have the `strtoq' function. */ +#ifndef HAVE_STRTOQ +#define HAVE_STRTOQ 1 +#endif + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#ifndef HAVE_SYS_STAT_H +#define HAVE_SYS_STAT_H 1 +#endif + +/* Define to 1 if you have the <sys/types.h> header file. */ +#ifndef HAVE_SYS_TYPES_H +#define HAVE_SYS_TYPES_H 1 +#endif + +/* Define to 1 if you have the <type_traits.h> header file. */ +/* #undef HAVE_TYPE_TRAITS_H */ + +/* Define to 1 if you have the <unistd.h> header file. */ +#ifndef HAVE_UNISTD_H +#define HAVE_UNISTD_H 1 +#endif + +/* Define to 1 if the system has the type `unsigned long long'. */ +#ifndef HAVE_UNSIGNED_LONG_LONG +#define HAVE_UNSIGNED_LONG_LONG 1 +#endif + +/* Define to 1 if you have the <windows.h> header file. */ +/* #undef HAVE_WINDOWS_H */ + +/* Define to 1 if you have the <zlib.h> header file. */ +#ifndef HAVE_ZLIB_H +#define HAVE_ZLIB_H 1 +#endif + +/* Define to 1 if you have the `_strtoi64' function. */ +/* #undef HAVE__STRTOI64 */ + +/* The value of LINK_SIZE determines the number of bytes used to store links + as offsets within the compiled regex. The default is 2, which allows for + compiled patterns up to 64K long. This covers the vast majority of cases. + However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows + for longer patterns in extreme cases. On systems that support it, + "configure" can be used to override this default. */ +#ifndef LINK_SIZE +#define LINK_SIZE 2 +#endif + +/* The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different limit. + The limit exists in order to catch runaway regular expressions that take + for ever to determine that they do not match. The default is set very large + so that it does not accidentally catch legitimate cases. On systems that + support it, "configure" can be used to override this default default. */ +#ifndef MATCH_LIMIT +#define MATCH_LIMIT 10000000 +#endif + +/* The above limit applies to all calls of match(), whether or not they + increase the recursion depth. In some environments it is desirable to limit + the depth of recursive calls of match() more strictly, in order to restrict + the maximum amount of stack (or heap, if NO_RECURSE is defined) that is + used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of + match(). To have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is + a runtime method for setting a different limit. On systems that support it, + "configure" can be used to override the default. */ +#ifndef MATCH_LIMIT_RECURSION +#define MATCH_LIMIT_RECURSION MATCH_LIMIT +#endif + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#ifndef MAX_NAME_COUNT +#define MAX_NAME_COUNT 10000 +#endif + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#ifndef MAX_NAME_SIZE +#define MAX_NAME_SIZE 32 +#endif + +/* The value of NEWLINE determines the newline character sequence. On systems + that support it, "configure" can be used to override the default, which is + 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2 + (ANYCRLF). */ +#ifndef NEWLINE +#define NEWLINE 10 +#endif + +/* PCRE uses recursive function calls to handle backtracking while matching. + This can sometimes be a problem on systems that have stacks of limited + size. Define NO_RECURSE to get a version that doesn't use recursion in the + match() function; instead it creates its own stack by steam using + pcre_recurse_malloc() to obtain memory from the heap. For more detail, see + the comments and other stuff just above the match() function. On systems + that support it, "configure" can be used to set this in the Makefile (use + --disable-stack-for-recursion). */ +/* #undef NO_RECURSE */ + +/* Name of package */ +#define PACKAGE "pcre" + +/* Define to the address where bug reports for this package should be sent. */ +#define PACKAGE_BUGREPORT "" + +/* Define to the full name of this package. */ +#define PACKAGE_NAME "PCRE" + +/* Define to the full name and version of this package. */ +#define PACKAGE_STRING "PCRE 7.9" + +/* Define to the one symbol short name of this package. */ +#define PACKAGE_TARNAME "pcre" + +/* Define to the version of this package. */ +#define PACKAGE_VERSION "7.9" + + +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +/* #undef PCRE_EXP_DEFN */ + +/* Define if linking statically (TODO: make nice with Libtool) */ +/* #undef PCRE_STATIC */ + +/* When calling PCRE via the POSIX interface, additional working storage is + required for holding the pointers to capturing substrings because PCRE + requires three integers per substring, whereas the POSIX interface provides + only two. If the number of expected substrings is small, the wrapper + function uses space on the stack, because this is faster than using + malloc() for each call. The threshold above which the stack is no longer + used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it, + "configure" can be used to override this default. */ +#ifndef POSIX_MALLOC_THRESHOLD +#define POSIX_MALLOC_THRESHOLD 10 +#endif + +/* Define to 1 if you have the ANSI C header files. */ +#ifndef STDC_HEADERS +#define STDC_HEADERS 1 +#endif + +/* Define to allow pcregrep to be linked with libbz2, so that it is able to + handle .bz2 files. */ +/* #undef SUPPORT_LIBBZ2 */ + +/* Define to allow pcretest to be linked with libreadline. */ +/* #undef SUPPORT_LIBREADLINE */ + +/* Define to allow pcregrep to be linked with libz, so that it is able to + handle .gz files. */ +/* #undef SUPPORT_LIBZ */ + +/* Define to enable support for Unicode properties */ +/* #undef SUPPORT_UCP */ + +/* Define to enable support for the UTF-8 Unicode encoding. This will work + even in an EBCDIC environment, but it is incompatible with the EBCDIC + macro. That is, PCRE can support *either* EBCDIC code *or* ASCII/UTF-8, but + not both at once. */ +/* #undef SUPPORT_UTF8 */ + +/* Version number of package */ +#ifndef VERSION +#define VERSION "7.9" +#endif + +/* Define to empty if `const' does not conform to ANSI C. */ +/* #undef const */ + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +/* #undef size_t */ Modified: freeswitch/trunk/libs/pcre/config.h.in ============================================================================== --- freeswitch/trunk/libs/pcre/config.h.in (original) +++ freeswitch/trunk/libs/pcre/config.h.in Mon Jun 8 18:51:30 2009 @@ -1,143 +1,248 @@ +/* config.h.in. Generated from configure.ac by autoheader. */ -/* On Unix-like systems config.in is converted by "configure" into config.h. + +/* On Unix-like systems config.h.in is converted by "configure" into config.h. Some other environments also support the use of "configure". PCRE is written in Standard C, but there are a few non-standard things it can cope with, allowing it to run on SunOS4 and other "close to standard" systems. -On a non-Unix-like system you should just copy this file into config.h, and set -up the macros the way you need them. You should normally change the definitions -of HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way -autoconf works, these cannot be made the defaults. If your system has bcopy() -and not memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE. -If your system has neither bcopy() nor memmove(), leave them both as 0; an -emulation function will be used. */ +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to +all of your compile commands, so that config.h is included at the start of +every source. + +Alternatively, you can avoid editing by using -D on the compiler command line +to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */ + +/* By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- time + default can be overridden by the user of PCRE at runtime. On systems that + support it, "configure" can be used to override the default. */ +#undef BSR_ANYCRLF /* If you are compiling for a system that uses EBCDIC instead of ASCII -character codes, define this macro as 1. On systems that can use "configure", -this can be done via --enable-ebcdic. */ + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic. PCRE will then assume + that all input strings are in EBCDIC. If you do not define this macro, PCRE + will assume input strings are ASCII or UTF-8 Unicode. It is not possible to + build a version of PCRE that supports both EBCDIC and UTF-8. */ +#undef EBCDIC -#ifndef EBCDIC -#define EBCDIC 0 -#endif - -/* If you are compiling for a system other than a Unix-like system or Win32, -and it needs some magic to be inserted before the definition of a function that -is exported by the library, define this macro to contain the relevant magic. If -you do not define this macro, it defaults to "extern" for a C compiler and -"extern C" for a C++ compiler on non-Win32 systems. This macro apears at the -start of every exported function that is part of the external API. It does not -appear on functions that are "external" in the C sense, but which are internal -to the library. */ +/* Define to 1 if you have the `bcopy' function. */ +#undef HAVE_BCOPY -/* #define PCRE_DATA_SCOPE */ +/* Define to 1 if you have the <bits/type_traits.h> header file. */ +#undef HAVE_BITS_TYPE_TRAITS_H -/* Define the following macro to empty if the "const" keyword does not work. */ +/* Define to 1 if you have the <bzlib.h> header file. */ +#undef HAVE_BZLIB_H -#undef const +/* Define to 1 if you have the <dirent.h> header file. */ +#undef HAVE_DIRENT_H -/* Define the following macro to "unsigned" if <stddef.h> does not define -size_t. */ +/* Define to 1 if you have the <dlfcn.h> header file. */ +#undef HAVE_DLFCN_H -#undef size_t +/* Define to 1 if you have the <inttypes.h> header file. */ +#undef HAVE_INTTYPES_H -/* The following two definitions are mainly for the benefit of SunOS4, which -does not have the strerror() or memmove() functions that should be present in -all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should -normally be defined with the value 1 for other systems, but unfortunately we -cannot make this the default because "configure" files generated by autoconf -will only change 0 to 1; they won't change 1 to 0 if the functions are not -found. */ - -#define HAVE_STRERROR 0 -#define HAVE_MEMMOVE 0 - -/* There are some non-Unix-like systems that don't even have bcopy(). If this -macro is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of -HAVE_BCOPY is not relevant. */ - -#define HAVE_BCOPY 0 - -/* The value of NEWLINE determines the newline character. The default is to -leave it up to the compiler, but some sites want to force a particular value. -On Unix-like systems, "configure" can be used to override this default. */ - -#ifndef NEWLINE -#define NEWLINE '\n' -#endif - -/* The value of LINK_SIZE determines the number of bytes used to store links as -offsets within the compiled regex. The default is 2, which allows for compiled -patterns up to 64K long. This covers the vast majority of cases. However, PCRE -can also be compiled to use 3 or 4 bytes instead. This allows for longer -patterns in extreme cases. On systems that support it, "configure" can be used -to override this default. */ - -#ifndef LINK_SIZE -#define LINK_SIZE 2 -#endif +/* Define to 1 if you have the <limits.h> header file. */ +#undef HAVE_LIMITS_H -/* When calling PCRE via the POSIX interface, additional working storage is -required for holding the pointers to capturing substrings because PCRE requires -three integers per substring, whereas the POSIX interface provides only two. If -the number of expected substrings is small, the wrapper function uses space on -the stack, because this is faster than using malloc() for each call. The -threshold above which the stack is no longer used is defined by POSIX_MALLOC_ -THRESHOLD. On systems that support it, "configure" can be used to override this -default. */ - -#ifndef POSIX_MALLOC_THRESHOLD -#define POSIX_MALLOC_THRESHOLD 10 -#endif +/* Define to 1 if the system has the type `long long'. */ +#undef HAVE_LONG_LONG -/* PCRE uses recursive function calls to handle backtracking while matching. -This can sometimes be a problem on systems that have stacks of limited size. -Define NO_RECURSE to get a version that doesn't use recursion in the match() -function; instead it creates its own stack by steam using pcre_recurse_malloc() -to obtain memory from the heap. For more detail, see the comments and other -stuff just above the match() function. On systems that support it, "configure" -can be used to set this in the Makefile (use --disable-stack-for-recursion). */ - -/* #define NO_RECURSE */ - -/* The value of MATCH_LIMIT determines the default number of times the internal -match() function can be called during a single execution of pcre_exec(). There -is a runtime interface for setting a different limit. The limit exists in order -to catch runaway regular expressions that take for ever to determine that they -do not match. The default is set very large so that it does not accidentally -catch legitimate cases. On systems that support it, "configure" can be used to -override this default default. */ - -#ifndef MATCH_LIMIT -#define MATCH_LIMIT 10000000 -#endif +/* Define to 1 if you have the `memmove' function. */ +#undef HAVE_MEMMOVE + +/* Define to 1 if you have the <memory.h> header file. */ +#undef HAVE_MEMORY_H + +/* Define to 1 if you have the <readline/history.h> header file. */ +#undef HAVE_READLINE_HISTORY_H + +/* Define to 1 if you have the <readline/readline.h> header file. */ +#undef HAVE_READLINE_READLINE_H + +/* Define to 1 if you have the <stdint.h> header file. */ +#undef HAVE_STDINT_H + +/* Define to 1 if you have the <stdlib.h> header file. */ +#undef HAVE_STDLIB_H + +/* Define to 1 if you have the `strerror' function. */ +#undef HAVE_STRERROR + +/* Define to 1 if you have the <string> header file. */ +#undef HAVE_STRING + +/* Define to 1 if you have the <strings.h> header file. */ +#undef HAVE_STRINGS_H + +/* Define to 1 if you have the <string.h> header file. */ +#undef HAVE_STRING_H + +/* Define to 1 if you have the `strtoll' function. */ +#undef HAVE_STRTOLL + +/* Define to 1 if you have the `strtoq' function. */ +#undef HAVE_STRTOQ + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#undef HAVE_SYS_STAT_H + +/* Define to 1 if you have the <sys/types.h> header file. */ +#undef HAVE_SYS_TYPES_H + +/* Define to 1 if you have the <type_traits.h> header file. */ +#undef HAVE_TYPE_TRAITS_H + +/* Define to 1 if you have the <unistd.h> header file. */ +#undef HAVE_UNISTD_H + +/* Define to 1 if the system has the type `unsigned long long'. */ +#undef HAVE_UNSIGNED_LONG_LONG + +/* Define to 1 if you have the <windows.h> header file. */ +#undef HAVE_WINDOWS_H + +/* Define to 1 if you have the <zlib.h> header file. */ +#undef HAVE_ZLIB_H + +/* Define to 1 if you have the `_strtoi64' function. */ +#undef HAVE__STRTOI64 + +/* The value of LINK_SIZE determines the number of bytes used to store links + as offsets within the compiled regex. The default is 2, which allows for + compiled patterns up to 64K long. This covers the vast majority of cases. + However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows + for longer patterns in extreme cases. On systems that support it, + "configure" can be used to override this default. */ +#undef LINK_SIZE + +/* The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different limit. + The limit exists in order to catch runaway regular expressions that take + for ever to determine that they do not match. The default is set very large + so that it does not accidentally catch legitimate cases. On systems that + support it, "configure" can be used to override this default default. */ +#undef MATCH_LIMIT /* The above limit applies to all calls of match(), whether or not they -increase the recursion depth. In some environments it is desirable to limit the -depth of recursive calls of match() more strictly, in order to restrict the -maximum amount of stack (or heap, if NO_RECURSE is defined) that is used. The -value of MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To -have any useful effect, it must be less than the value of MATCH_LIMIT. There is -a runtime method for setting a different limit. On systems that support it, -"configure" can be used to override this default default. */ - -#ifndef MATCH_LIMIT_RECURSION -#define MATCH_LIMIT_RECURSION MATCH_LIMIT -#endif - -/* These three limits are parameterized just in case anybody ever wants to -change them. Care must be taken if they are increased, because they guard -against integer overflow caused by enormously large patterns. */ - -#ifndef MAX_NAME_SIZE -#define MAX_NAME_SIZE 32 -#endif - -#ifndef MAX_NAME_COUNT -#define MAX_NAME_COUNT 10000 -#endif - -#ifndef MAX_DUPLENGTH -#define MAX_DUPLENGTH 30000 -#endif + increase the recursion depth. In some environments it is desirable to limit + the depth of recursive calls of match() more strictly, in order to restrict + the maximum amount of stack (or heap, if NO_RECURSE is defined) that is + used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of + match(). To have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is + a runtime method for setting a different limit. On systems that support it, + "configure" can be used to override the default. */ +#undef MATCH_LIMIT_RECURSION + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#undef MAX_NAME_COUNT + +/* This limit is parameterized just in case anybody ever wants to change it. + Care must be taken if it is increased, because it guards against integer + overflow caused by enormously large patterns. */ +#undef MAX_NAME_SIZE + +/* The value of NEWLINE determines the newline character sequence. On systems + that support it, "configure" can be used to override the default, which is + 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2 + (ANYCRLF). */ +#undef NEWLINE -/* End */ +/* PCRE uses recursive function calls to handle backtracking while matching. + This can sometimes be a problem on systems that have stacks of limited + size. Define NO_RECURSE to get a version that doesn't use recursion in the + match() function; instead it creates its own stack by steam using + pcre_recurse_malloc() to obtain memory from the heap. For more detail, see + the comments and other stuff just above the match() function. On systems + that support it, "configure" can be used to set this in the Makefile (use + --disable-stack-for-recursion). */ +#undef NO_RECURSE + +/* Name of package */ +#undef PACKAGE + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + + +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +#undef PCRE_EXP_DEFN + +/* Define if linking statically (TODO: make nice with Libtool) */ +#undef PCRE_STATIC + +/* When calling PCRE via the POSIX interface, additional working storage is + required for holding the pointers to capturing substrings because PCRE + requires three integers per substring, whereas the POSIX interface provides + only two. If the number of expected substrings is small, the wrapper + function uses space on the stack, because this is faster than using + malloc() for each call. The threshold above which the stack is no longer + used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it, + "configure" can be used to override this default. */ +#undef POSIX_MALLOC_THRESHOLD + +/* Define to 1 if you have the ANSI C header files. */ +#undef STDC_HEADERS + +/* Define to allow pcregrep to be linked with libbz2, so that it is able to + handle .bz2 files. */ +#undef SUPPORT_LIBBZ2 + +/* Define to allow pcretest to be linked with libreadline. */ +#undef SUPPORT_LIBREADLINE + +/* Define to allow pcregrep to be linked with libz, so that it is able to + handle .gz files. */ +#undef SUPPORT_LIBZ + +/* Define to enable support for Unicode properties */ +#undef SUPPORT_UCP + +/* Define to enable support for the UTF-8 Unicode encoding. This will work + even in an EBCDIC environment, but it is incompatible with the EBCDIC + macro. That is, PCRE can support *either* EBCDIC code *or* ASCII/UTF-8, but + not both at once. */ +#undef SUPPORT_UTF8 + +/* Version number of package */ +#undef VERSION + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +#undef size_t Modified: freeswitch/trunk/libs/pcre/configure.ac ============================================================================== --- freeswitch/trunk/libs/pcre/configure.ac (original) +++ freeswitch/trunk/libs/pcre/configure.ac Mon Jun 8 18:51:30 2009 @@ -1,91 +1,282 @@ - dnl Process this file with autoconf to produce a configure script. -dnl This configure.in file has been hacked around quite a lot as a result of -dnl patches that various people have sent to me (PH). Sometimes the information -dnl I get is contradictory. I've tried to put in comments that explain things, -dnl but in some cases the information is second-hand and I have no way of -dnl verifying it. I am not an autoconf or libtool expert! +dnl NOTE FOR MAINTAINERS: Do not use major or minor version numbers with +dnl leading zeros, because they may be treated as octal constants. The +dnl PCRE_PRERELEASE feature is for identifying release candidates. It might +dnl be defined as -RC2, for example. For real releases, it should be defined +dnl empty. + +m4_define(pcre_major, [7]) +m4_define(pcre_minor, [9]) +m4_define(pcre_prerelease, []) +m4_define(pcre_date, [2009-04-11]) + +# Libtool shared library interface versions (current:revision:age) +m4_define(libpcre_version, [0:1:0]) +m4_define(libpcreposix_version, [0:0:0]) +m4_define(libpcrecpp_version, [0:0:0]) -dnl This is required at the start; the name is the name of a file -dnl it should be seeing, to verify it is in the same directory. +AC_PREREQ(2.57) +AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre) +AC_CONFIG_SRCDIR([pcre.h.in]) +AM_INIT_AUTOMAKE([dist-bzip2 dist-zip]) +AC_CONFIG_HEADERS(config.h) + +# The default CFLAGS and CXXFLAGS in Autoconf are "-g -O2" for gcc and just +# "-g" for any other compiler. There doesn't seem to be a standard way of +# getting rid of the -g (which I don't think is needed for a production +# library). This fudge seems to achieve the necessary. First, we remember the +# externally set values of CFLAGS and CXXFLAGS. Then call the AC_PROG_CC and +# AC_PROG_CXX macros to find the compilers - if CFLAGS and CXXFLAGS are not +# set, they will be set to Autoconf's defaults. Afterwards, if the original +# values were not set, remove the -g from the Autoconf defaults. +# (PH 02-May-07) -AC_INIT(dftables.c) -AC_CONFIG_SRCDIR([pcre.h]) +remember_set_CFLAGS="$CFLAGS" +remember_set_CXXFLAGS="$CXXFLAGS" -dnl A safety precaution +AC_PROG_CC +AC_PROG_CXX -AC_PREREQ(2.57) +if test "x$remember_set_CFLAGS" = "x" +then + if test "$CFLAGS" = "-g -O2" + then + CFLAGS="-O2" + elif test "$CFLAGS" = "-g" + then + CFLAGS="" + fi +fi -dnl Arrange to build config.h from config.h.in. -dnl Manual says this macro should come right after AC_INIT. -AC_CONFIG_HEADER(config.h) +if test "x$remember_set_CXXFLAGS" = "x" +then + if test "$CXXFLAGS" = "-g -O2" + then + CXXFLAGS="-O2" + elif test "$CXXFLAGS" = "-g" + then + CXXFLAGS="" + fi +fi -dnl Default values for miscellaneous macros +# AC_PROG_CXX will return "g++" even if no c++ compiler is installed. +# Check for that case, and just disable c++ code if g++ doesn't run. +AC_LANG_PUSH(C++) +AC_COMPILE_IFELSE(AC_LANG_PROGRAM([],[]),, CXX=""; CXXCP=""; CXXFLAGS="") +AC_LANG_POP -POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 +AC_PROG_INSTALL +AC_LIBTOOL_WIN32_DLL +AC_PROG_LIBTOOL +AC_PROG_LN_S -dnl Provide versioning information for libtool shared libraries that -dnl are built by default on Unix systems. +PCRE_MAJOR="pcre_major" +PCRE_MINOR="pcre_minor" +PCRE_PRERELEASE="pcre_prerelease" +PCRE_DATE="pcre_date" + +AC_SUBST(PCRE_MAJOR) +AC_SUBST(PCRE_MINOR) +AC_SUBST(PCRE_PRERELEASE) +AC_SUBST(PCRE_DATE) -PCRE_LIB_VERSION=0:1:0 -PCRE_POSIXLIB_VERSION=0:0:0 -PCRE_CPPLIB_VERSION=0:0:0 +# Set a more sensible default value for $(htmldir). +if test "x$htmldir" = 'x${docdir}' +then + htmldir='${docdir}/html' +fi -dnl Find the PCRE version from the pcre.h file. The PCRE_VERSION variable is -dnl substituted in pcre-config.in. +# Handle --disable-cpp +AC_ARG_ENABLE(cpp, + AS_HELP_STRING([--disable-cpp], + [disable C++ support]), + , enable_cpp=yes) + +# Handle --enable-rebuild-chartables +AC_ARG_ENABLE(rebuild-chartables, + AS_HELP_STRING([--enable-rebuild-chartables], + [rebuild character tables in current locale]), + , enable_rebuild_chartables=no) -PCRE_MAJOR=`grep '#define PCRE_MAJOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_MINOR=`grep '#define PCRE_MINOR' ${srcdir}/pcre.h | cut -c 29-` -PCRE_PRERELEASE=`grep '#define PCRE_PRERELEASE' ${srcdir}/pcre.h | cut -c 29-` -PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR}${PCRE_PRERELEASE} +# Handle --enable-utf8 (disabled by default) +AC_ARG_ENABLE(utf8, + AS_HELP_STRING([--enable-utf8], + [enable UTF-8 support (incompatible with --enable-ebcdic)]), + , enable_utf8=unset) -dnl Handle --disable-cpp +# Handle --enable-unicode-properties +AC_ARG_ENABLE(unicode-properties, + AS_HELP_STRING([--enable-unicode-properties], + [enable Unicode properties support (implies --enable-utf8)]), + , enable_unicode_properties=no) + +# Handle --enable-newline=NL +dnl AC_ARG_ENABLE(newline, +dnl AS_HELP_STRING([--enable-newline=NL], +dnl [use NL as newline (lf, cr, crlf, anycrlf, any; default=lf)]), +dnl , enable_newline=lf) -AC_ARG_ENABLE(cpp, -[ --disable-cpp disable C++ support], -want_cpp="$enableval", want_cpp=yes) +# Separate newline options +ac_pcre_newline=lf +AC_ARG_ENABLE(newline-is-cr, + AS_HELP_STRING([--enable-newline-is-cr], + [use CR as newline character]), + ac_pcre_newline=cr) +AC_ARG_ENABLE(newline-is-lf, + AS_HELP_STRING([--enable-newline-is-lf], + [use LF as newline character (default)]), + ac_pcre_newline=lf) +AC_ARG_ENABLE(newline-is-crlf, + AS_HELP_STRING([--enable-newline-is-crlf], + [use CRLF as newline sequence]), + ac_pcre_newline=crlf) +AC_ARG_ENABLE(newline-is-anycrlf, + AS_HELP_STRING([--enable-newline-is-anycrlf], + [use CR, LF, or CRLF as newline sequence]), + ac_pcre_newline=anycrlf) +AC_ARG_ENABLE(newline-is-any, + AS_HELP_STRING([--enable-newline-is-any], + [use any valid Unicode newline sequence]), + ac_pcre_newline=any) +enable_newline="$ac_pcre_newline" + +# Handle --enable-bsr-anycrlf +AC_ARG_ENABLE(bsr-anycrlf, + AS_HELP_STRING([--enable-bsr-anycrlf], + [\R matches only CR, LF, CRLF by default]), + , enable_bsr_anycrlf=no) -dnl Checks for programs. +# Handle --enable-ebcdic +AC_ARG_ENABLE(ebcdic, + AS_HELP_STRING([--enable-ebcdic], + [assume EBCDIC coding rather than ASCII; incompatible with --enable-utf8; use only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]), + , enable_ebcdic=no) -AC_PROG_CC +# Handle --disable-stack-for-recursion +AC_ARG_ENABLE(stack-for-recursion, + AS_HELP_STRING([--disable-stack-for-recursion], + [don't use stack recursion when matching]), + , enable_stack_for_recursion=yes) + +# Handle --enable-pcregrep-libz +AC_ARG_ENABLE(pcregrep-libz, + AS_HELP_STRING([--enable-pcregrep-libz], + [link pcregrep with libz to handle .gz files]), + , enable_pcregrep_libz=no) + +# Handle --enable-pcregrep-libbz2 +AC_ARG_ENABLE(pcregrep-libbz2, + AS_HELP_STRING([--enable-pcregrep-libbz2], + [link pcregrep with libbz2 to handle .bz2 files]), + , enable_pcregrep_libbz2=no) + +# Handle --enable-pcretest-libreadline +AC_ARG_ENABLE(pcretest-libreadline, + AS_HELP_STRING([--enable-pcretest-libreadline], + [link pcretest with libreadline]), + , enable_pcretest_libreadline=no) -dnl Test for C++ for the C++ wrapper libpcrecpp. It seems, however, that -dnl AC_PROC_CXX will set $CXX to "g++" when no C++ compiler is installed, even -dnl though that is completely bogus. (This may happen only on certain systems -dnl with certain versions of autoconf, of course.) An attempt to include this -dnl test inside a check for want_cpp was criticized by a libtool expert, who -dnl tells me that it isn't allowed. +# Handle --with-posix-malloc-threshold=NBYTES +AC_ARG_WITH(posix-malloc-threshold, + AS_HELP_STRING([--with-posix-malloc-threshold=NBYTES], + [threshold for POSIX malloc usage (default=10)]), + , with_posix_malloc_threshold=10) -AC_PROG_CXX +# Handle --with-link-size=N +AC_ARG_WITH(link-size, + AS_HELP_STRING([--with-link-size=N], + [internal link size (2, 3, or 4 allowed; default=2)]), + , with_link_size=2) -dnl The icc compiler has the same options as gcc, so let the rest of the -dnl configure script think it has gcc when setting up dnl options etc. -dnl This is a nasty hack which no longer seems necessary with the update -dnl to the latest libtool files, so I have commented it out. -dnl -dnl if test "$CC" = "icc" ; then GCC=yes ; fi +# Handle --with-match-limit=N +AC_ARG_WITH(match-limit, + AS_HELP_STRING([--with-match-limit=N], + [default limit on internal looping (default=10000000)]), + , with_match_limit=10000000) + +# Handle --with-match-limit_recursion=N +# +# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION +# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric +# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some +# different numeric value (or even the same numeric value as MATCH_LIMIT, +# though no longer defined in terms of the latter). +# +AC_ARG_WITH(match-limit-recursion, + AS_HELP_STRING([--with-match-limit-recursion=N], + [default limit on internal recursion (default=MATCH_LIMIT)]), + , with_match_limit_recursion=MATCH_LIMIT) + +# Make sure that if enable_unicode_properties was set, that UTF-8 support +# is enabled. +# +if test "x$enable_unicode_properties" = "xyes" +then + if test "x$enable_utf8" = "xno" + then + AC_MSG_ERROR([support for Unicode properties requires UTF-8 support]) + fi + enable_utf8=yes +fi -AC_PROG_INSTALL -AC_LIBTOOL_WIN32_DLL -AC_PROG_LIBTOOL +if test "x$enable_utf8" = "xunset" +then + enable_utf8=no +fi + +# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# Also check that UTF-8 support is not requested, because PCRE cannot handle +# EBCDIC and UTF-8 in the same build. To do so it would need to use different +# character constants depending on the mode. +# +if test "x$enable_ebcdic" = "xyes" +then + enable_rebuild_chartables=yes + if test "x$enable_utf8" = "xyes" + then + AC_MSG_ERROR([support for EBCDIC and UTF-8 cannot be enabled at the same time]) + fi +fi + +# Convert the newline identifier into the appropriate integer value. +case "$enable_newline" in + lf) ac_pcre_newline_value=10 ;; + cr) ac_pcre_newline_value=13 ;; + crlf) ac_pcre_newline_value=3338 ;; + anycrlf) ac_pcre_newline_value=-2 ;; + any) ac_pcre_newline_value=-1 ;; + *) + AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option]) + ;; +esac + +# Check argument to --with-link-size +case "$with_link_size" in + 2|3|4) ;; + *) + AC_MSG_ERROR([invalid argument \"$with_link_size\" to --with-link-size option]) + ;; +esac -dnl We need to find a compiler for compiling a program to run on the local host -dnl while building. It needs to be different from CC when cross-compiling. -dnl There is a macro called AC_PROG_CC_FOR_BUILD in the GNU archive for -dnl figuring this out automatically. Unfortunately, it does not work with the -dnl latest versions of autoconf. So for the moment, we just default to the -dnl same values as the "main" compiler. People who are cross-compiling will -dnl just have to adjust the Makefile by hand or set these values when they -dnl run "configure". - -CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} -CXX_FOR_BUILD=${CXX_FOR_BUILD:-'$(CXX)'} -CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} -CPPFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CPPFLAGS)'} -CXXFLAGS_FOR_BUILD=${CXXFLAGS_FOR_BUILD:-'$(CXXFLAGS)'} -BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} -BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} +AH_TOP([ +/* On Unix-like systems config.h.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to +all of your compile commands, so that config.h is included at the start of +every source. + +Alternatively, you can avoid editing by using -D on the compiler command line +to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */]) AC_DEFUN([AX_COMPILER_VENDOR], [ @@ -116,217 +307,381 @@ fi fi -dnl Checks for header files. - +# Checks for header files. AC_HEADER_STDC -AC_CHECK_HEADERS(limits.h) - -dnl The files below are C++ header files. One person told me (PH) that -dnl AC_LANG_CPLUSPLUS unsets CXX if it was explicitly set to something which -dnl doesn't work. However, this doesn't always seem to be the case. +AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h windows.h) -if test "x$want_cpp" = "xyes" -a -n "$CXX" +# The files below are C++ header files. +pcre_have_type_traits="0" +pcre_have_bits_type_traits="0" +if test "x$enable_cpp" = "xyes" -a -n "$CXX" then -AC_LANG_SAVE -AC_LANG_CPLUSPLUS +AC_LANG_PUSH(C++) -dnl We could be more clever here, given we're doing AC_SUBST with this -dnl (eg set a var to be the name of the include file we want). But we're not -dnl so it's easy to change back to 'regular' autoconf vars if we needed to. +# Older versions of pcre defined pcrecpp::no_arg, but in new versions +# it's called pcrecpp::RE::no_arg. For backwards ABI compatibility, +# we want to make one an alias for the other. Different systems do +# this in different ways. Some systems, for instance, can do it via +# a linker flag: -alias (for os x 10.5) or -i (for os x <=10.4). +OLD_LDFLAGS="$LDFLAGS" +for flag in "-alias,__ZN7pcrecpp2RE6no_argE,__ZN7pcrecpp6no_argE" \ + "-i__ZN7pcrecpp6no_argE:__ZN7pcrecpp2RE6no_argE"; do + AC_MSG_CHECKING([for alias support in the linker]) + LDFLAGS="$OLD_LDFLAGS -Wl,$flag" + # We try to run the linker with this new ld flag. If the link fails, + # we give up and remove the new flag from LDFLAGS. + AC_LINK_IFELSE(AC_LANG_PROGRAM([namespace pcrecpp { + class RE { static int no_arg; }; + int RE::no_arg; + }], + []), + [AC_MSG_RESULT([yes]); + EXTRA_LIBPCRECPP_LDFLAGS="$EXTRA_LIBPCRECPP_LDFLAGS -Wl,$flag"; + break;], + AC_MSG_RESULT([no])) +done +LDFLAGS="$OLD_LDFLAGS" + +# We could be more clever here, given we're doing AC_SUBST with this +# (eg set a var to be the name of the include file we want). But we're not +# so it's easy to change back to 'regular' autoconf vars if we needed to. AC_CHECK_HEADERS(string, [pcre_have_cpp_headers="1"], [pcre_have_cpp_headers="0"]) AC_CHECK_HEADERS(bits/type_traits.h, [pcre_have_bits_type_traits="1"], [pcre_have_bits_type_traits="0"]) AC_CHECK_HEADERS(type_traits.h, [pcre_have_type_traits="1"], [pcre_have_type_traits="0"]) -dnl Using AC_SUBST eliminates the need to include config.h in a public .h file -AC_SUBST(pcre_have_bits_type_traits) -AC_SUBST(pcre_have_type_traits) -AC_LANG_RESTORE -fi -dnl From the above, we now have enough info to know if C++ is fully installed -if test "x$want_cpp" = "xyes" -a -n "$CXX" -a "$pcre_have_cpp_headers" = 1; then - MAYBE_CPP_TARGETS='$(CPP_TARGETS)' - HAVE_CPP= -else - MAYBE_CPP_TARGETS= - HAVE_CPP="#" +AC_LANG_POP fi -AC_SUBST(MAYBE_CPP_TARGETS) -AC_SUBST(HAVE_CPP) +# Using AC_SUBST eliminates the need to include config.h in a public .h file +AC_SUBST(pcre_have_type_traits) +AC_SUBST(pcre_have_bits_type_traits) + +# Conditional compilation +AM_CONDITIONAL(WITH_PCRE_CPP, test "x$enable_cpp" = "xyes") +AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes") -dnl Checks for typedefs, structures, and compiler characteristics. +# Checks for typedefs, structures, and compiler characteristics. AC_C_CONST AC_TYPE_SIZE_T -AC_CHECK_TYPES([long long], [pcre_have_long_long="1"], [pcre_have_long_long="0"]) -AC_CHECK_TYPES([unsigned long long], [pcre_have_ulong_long="1"], [pcre_have_ulong_long="0"]) +pcre_have_strotolonglong=0 +AC_CHECK_FUNCS(strtoq strtoll _strtoi64, [pcre_have_strotolonglong="1"; break]) +# If we can't convert a string to a long long, pretend we don't even +# have a long long. +if test $pcre_have_strotolonglong = "0"; then + pcre_have_long_long="0" + pcre_have_ulong_long="0" +else + AC_CHECK_TYPES([long long], + [pcre_have_long_long="1"], + [pcre_have_long_long="0"]) + AC_CHECK_TYPES([unsigned long long], + [pcre_have_ulong_long="1"], + [pcre_have_ulong_long="0"]) +fi AC_SUBST(pcre_have_long_long) AC_SUBST(pcre_have_ulong_long) -dnl Checks for library functions. +# Checks for library functions. -AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll) +AC_CHECK_FUNCS(bcopy memmove strerror) -dnl Handle --enable-utf8 +# Check for the availability of libz (aka zlib) -AC_ARG_ENABLE(utf8, -[ --enable-utf8 enable UTF8 support], -if test "$enableval" = "yes"; then - UTF8=-DSUPPORT_UTF8 -fi -) +AC_CHECK_HEADERS([zlib.h], [HAVE_ZLIB_H=1]) +AC_CHECK_LIB([z], [gzopen], [HAVE_LIBZ=1]) -dnl Handle --enable-unicode-properties +# Check for the availability of libbz2 -AC_ARG_ENABLE(unicode-properties, -[ --enable-unicode-properties enable Unicode properties support], -if test "$enableval" = "yes"; then - UCP=-DSUPPORT_UCP -fi -) - -dnl Handle --enable-newline-is-cr - -AC_ARG_ENABLE(newline-is-cr, -[ --enable-newline-is-cr use CR as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=13 -fi -) +AC_CHECK_HEADERS([bzlib.h], [HAVE_BZLIB_H=1]) +AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1]) -dnl Handle --enable-newline-is-lf +# Check for the availabiity of libreadline -AC_ARG_ENABLE(newline-is-lf, -[ --enable-newline-is-lf use LF as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=10 -fi -) +AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_H=1]) +AC_CHECK_HEADERS([readline/history.h], [HAVE_HISTORY_H=1]) +AC_CHECK_LIB([readline], [readline], [HAVE_LIB_READLINE=1]) -dnl Handle --enable-newline-is-crlf +# This facilitates -ansi builds under Linux +dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc]) -AC_ARG_ENABLE(newline-is-crlf, -[ --enable-newline-is-crlf use CRLF as the newline sequence], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=3338 -fi -) - -dnl Handle --enable-ebcdic - -AC_ARG_ENABLE(ebcdic, -[ --enable-ebcdic assume EBCDIC coding rather than ASCII], -if test "$enableval" == "yes"; then - EBCDIC=-DEBCDIC=1 -fi -) - -dnl Handle --disable-stack-for-recursion - -AC_ARG_ENABLE(stack-for-recursion, -[ --disable-stack-for-recursion disable use of stack recursion when matching], -if test "$enableval" = "no"; then - NO_RECURSE=-DNO_RECURSE +if test "x$enable_shared" = "xno" ; then + AC_DEFINE([PCRE_STATIC], [1], [ + Define if linking statically (TODO: make nice with Libtool)]) fi -) - -dnl There doesn't seem to be a straightforward way of having parameters -dnl that set values, other than fudging the --with thing. So that's what -dnl I've done. -dnl Handle --with-posix-malloc-threshold=n +# Here is where pcre specific defines are handled -AC_ARG_WITH(posix-malloc-threshold, -[ --with-posix-malloc-threshold=10 threshold for POSIX malloc usage], - POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval -) - -dnl Handle --with-link-size=n - -AC_ARG_WITH(link-size, -[ --with-link-size=2 internal link size (2, 3, or 4 allowed)], - LINK_SIZE=-DLINK_SIZE=$withval -) - -dnl Handle --with-match-limit=n - -AC_ARG_WITH(match-limit, -[ --with-match-limit=10000000 default limit on internal looping], - MATCH_LIMIT=-DMATCH_LIMIT=$withval -) - -dnl Handle --with-match-limit_recursion=n - -AC_ARG_WITH(match-limit-recursion, -[ --with-match-limit-recursion=10000000 default limit on internal recursion], - MATCH_LIMIT_RECURSION=-DMATCH_LIMIT_RECURSION=$withval -) - -dnl Unicode character property support implies UTF-8 support +if test "$enable_utf8" = "yes"; then + AC_DEFINE([SUPPORT_UTF8], [], [ + Define to enable support for the UTF-8 Unicode encoding. This will + work even in an EBCDIC environment, but it is incompatible with + the EBCDIC macro. That is, PCRE can support *either* EBCDIC code + *or* ASCII/UTF-8, but not both at once.]) +fi + +if test "$enable_unicode_properties" = "yes"; then + AC_DEFINE([SUPPORT_UCP], [], [ + Define to enable support for Unicode properties]) +fi + +if test "$enable_stack_for_recursion" = "no"; then + AC_DEFINE([NO_RECURSE], [], [ + PCRE uses recursive function calls to handle backtracking while + matching. This can sometimes be a problem on systems that have + stacks of limited size. Define NO_RECURSE to get a version that + doesn't use recursion in the match() function; instead it creates + its own stack by steam using pcre_recurse_malloc() to obtain memory + from the heap. For more detail, see the comments and other stuff + just above the match() function. On systems that support it, + "configure" can be used to set this in the Makefile + (use --disable-stack-for-recursion).]) +fi + +if test "$enable_pcregrep_libz" = "yes"; then + AC_DEFINE([SUPPORT_LIBZ], [], [ + Define to allow pcregrep to be linked with libz, so that it is + able to handle .gz files.]) +fi + +if test "$enable_pcregrep_libbz2" = "yes"; then + AC_DEFINE([SUPPORT_LIBBZ2], [], [ + Define to allow pcregrep to be linked with libbz2, so that it is + able to handle .bz2 files.]) +fi + +if test "$enable_pcretest_libreadline" = "yes"; then + AC_DEFINE([SUPPORT_LIBREADLINE], [], [ + Define to allow pcretest to be linked with libreadline.]) +fi + +AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [ + The value of NEWLINE determines the newline character sequence. On + systems that support it, "configure" can be used to override the + default, which is 10. The possible values are 10 (LF), 13 (CR), + 3338 (CRLF), -1 (ANY), or -2 (ANYCRLF).]) + +if test "$enable_bsr_anycrlf" = "yes"; then + AC_DEFINE([BSR_ANYCRLF], [], [ + By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- + time default can be overridden by the user of PCRE at runtime. On + systems that support it, "configure" can be used to override the + default.]) +fi + +AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ + The value of LINK_SIZE determines the number of bytes used to store + links as offsets within the compiled regex. The default is 2, which + allows for compiled patterns up to 64K long. This covers the vast + majority of cases. However, PCRE can also be compiled to use 3 or 4 + bytes instead. This allows for longer patterns in extreme cases. On + systems that support it, "configure" can be used to override this default.]) + +AC_DEFINE_UNQUOTED([POSIX_MALLOC_THRESHOLD], [$with_posix_malloc_threshold], [ + When calling PCRE via the POSIX interface, additional working storage + is required for holding the pointers to capturing substrings because + PCRE requires three integers per substring, whereas the POSIX + interface provides only two. If the number of expected substrings is + small, the wrapper function uses space on the stack, because this is + faster than using malloc() for each call. The threshold above which + the stack is no longer used is defined by POSIX_MALLOC_THRESHOLD. On + systems that support it, "configure" can be used to override this + default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [ + The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different + limit. The limit exists in order to catch runaway regular + expressions that take for ever to determine that they do not match. + The default is set very large so that it does not accidentally catch + legitimate cases. On systems that support it, "configure" can be + used to override this default default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT_RECURSION], [$with_match_limit_recursion], [ + The above limit applies to all calls of match(), whether or not they + increase the recursion depth. In some environments it is desirable + to limit the depth of recursive calls of match() more strictly, in + order to restrict the maximum amount of stack (or heap, if + NO_RECURSE is defined) that is used. The value of + MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To + have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. + There is a runtime method for setting a different limit. On systems + that support it, "configure" can be used to override the default.]) + +AC_DEFINE([MAX_NAME_SIZE], [32], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AC_DEFINE([MAX_NAME_COUNT], [10000], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AH_VERBATIM([PCRE_EXP_DEFN], [ +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +#undef PCRE_EXP_DEFN]) + +if test "$enable_ebcdic" = "yes"; then + AC_DEFINE_UNQUOTED([EBCDIC], [], [ + If you are compiling for a system that uses EBCDIC instead of ASCII + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic. PCRE will then + assume that all input strings are in EBCDIC. If you do not define + this macro, PCRE will assume input strings are ASCII or UTF-8 Unicode. + It is not possible to build a version of PCRE that supports both + EBCDIC and UTF-8.]) +fi + +# Platform specific issues +NO_UNDEFINED= +EXPORT_ALL_SYMBOLS= +case $host_os in + cygwin* | mingw* ) + if test X"$enable_shared" = Xyes; then + NO_UNDEFINED="-no-undefined" + EXPORT_ALL_SYMBOLS="-Wl,--export-all-symbols" + fi + ;; +esac -if test "$UCP" != "" ; then - UTF8=-DSUPPORT_UTF8 -fi +# The extra LDFLAGS for each particular library +# (Note: The libpcre*_version bits are m4 variables, assigned above) -dnl "Export" these variables +EXTRA_LIBPCRE_LDFLAGS="$EXTRA_LIBPCRE_LDFLAGS \ + $NO_UNDEFINED -version-info libpcre_version" -AC_SUBST(BUILD_EXEEXT) -AC_SUBST(BUILD_OBJEXT) -AC_SUBST(CC_FOR_BUILD) -AC_SUBST(CXX_FOR_BUILD) -AC_SUBST(CFLAGS_FOR_BUILD) -AC_SUBST(CXXFLAGS_FOR_BUILD) -AC_SUBST(CXXLDFLAGS) -AC_SUBST(EBCDIC) -AC_SUBST(HAVE_MEMMOVE) -AC_SUBST(HAVE_STRERROR) -AC_SUBST(LINK_SIZE) -AC_SUBST(MATCH_LIMIT) -AC_SUBST(MATCH_LIMIT_RECURSION) -AC_SUBST(NEWLINE) -AC_SUBST(NO_RECURSE) -AC_SUBST(PCRE_LIB_VERSION) -AC_SUBST(PCRE_POSIXLIB_VERSION) -AC_SUBST(PCRE_CPPLIB_VERSION) -AC_SUBST(PCRE_VERSION) -AC_SUBST(POSIX_MALLOC_THRESHOLD) -AC_SUBST(UCP) -AC_SUBST(UTF8) +EXTRA_LIBPCREPOSIX_LDFLAGS="$EXTRA_LIBPCREPOSIX_LDFLAGS \ + $NO_UNDEFINED -version-info libpcreposix_version" -dnl Stuff to make MinGW work better. Special treatment is no longer -dnl needed for Cygwin. +EXTRA_LIBPCRECPP_LDFLAGS="$EXTRA_LIBPCRECPP_LDFLAGS \ + $NO_UNDEFINED -version-info libpcrecpp_version \ + $EXPORT_ALL_SYMBOLS" + +AC_SUBST(EXTRA_LIBPCRE_LDFLAGS) +AC_SUBST(EXTRA_LIBPCREPOSIX_LDFLAGS) +AC_SUBST(EXTRA_LIBPCRECPP_LDFLAGS) + +# When we run 'make distcheck', use these arguments. +DISTCHECK_CONFIGURE_FLAGS="--enable-cpp --enable-unicode-properties" +AC_SUBST(DISTCHECK_CONFIGURE_FLAGS) + +# Check that, if --enable-pcregrep-libz or --enable-pcregrep-libbz2 is +# specified, the relevant library is available. + +if test "$enable_pcregrep_libz" = "yes"; then + if test "$HAVE_ZLIB_H" != "1"; then + echo "** Cannot --enable-pcregrep-libz because zlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBZ" != "1"; then + echo "** Cannot --enable-pcregrep-libz because libz was not found" + exit 1 + fi + LIBZ="-lz" +fi +AC_SUBST(LIBZ) + +if test "$enable_pcregrep_libbz2" = "yes"; then + if test "$HAVE_BZLIB_H" != "1"; then + echo "** Cannot --enable-pcregrep-libbz2 because bzlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBBZ2" != "1"; then + echo "** Cannot --enable-pcregrep-libbz2 because libbz2 was not found" + exit 1 + fi + LIBBZ2="-lbz2" +fi +AC_SUBST(LIBBZ2) + +# Similarly for --enable-pcretest-readline + +if test "$enable_pcretest_libreadline" = "yes"; then + if test "$HAVE_READLINE_H" != "1"; then + echo "** Cannot --enable-pcretest-readline because readline/readline.h was not found." + exit 1 + fi + if test "$HAVE_HISTORY_H" != "1"; then + echo "** Cannot --enable-pcretest-readline because readline/history.h was not found." + exit 1 + fi + LIBREADLINE="-lreadline" +fi +AC_SUBST(LIBREADLINE) + +# Produce these files, in addition to config.h. +AC_CONFIG_FILES( + Makefile + libpcre.pc + libpcrecpp.pc + pcre-config + pcre.h + pcre_stringpiece.h + pcrecpparg.h +) + +# Make the generated script files executable. +AC_CONFIG_COMMANDS([script-chmod], [chmod a+x pcre-config]) + +# Make sure that pcre_chartables.c is removed in case the method for +# creating it was changed by reconfiguration. +AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre_chartables.c]) + +AC_OUTPUT + +# Print out a nice little message after configure is run displaying your +# chosen options. + +cat <<EOF + +$PACKAGE-$VERSION configuration summary: + + Install prefix .................. : ${prefix} + C preprocessor .................. : ${CPP} + C compiler ...................... : ${CC} + C++ preprocessor ................ : ${CXXCPP} + C++ compiler .................... : ${CXX} + Linker .......................... : ${LD} + C preprocessor flags ............ : ${CPPFLAGS} + C compiler flags ................ : ${CFLAGS} + C++ compiler flags .............. : ${CXXFLAGS} + Linker flags .................... : ${LDFLAGS} + Extra libraries ................. : ${LIBS} + + Build C++ library ............... : ${enable_cpp} + Enable UTF-8 support ............ : ${enable_utf8} + Unicode properties .............. : ${enable_unicode_properties} + Newline char/sequence ........... : ${enable_newline} + \R matches only ANYCRLF ......... : ${enable_bsr_anycrlf} + EBCDIC coding ................... : ${enable_ebcdic} + Rebuild char tables ............. : ${enable_rebuild_chartables} + Use stack recursion ............. : ${enable_stack_for_recursion} + POSIX mem threshold ............. : ${with_posix_malloc_threshold} + Internal link size .............. : ${with_link_size} + Match limit ..................... : ${with_match_limit} + Match limit recursion ........... : ${with_match_limit_recursion} + Build shared libs ............... : ${enable_shared} + Build static libs ............... : ${enable_static} + Link pcregrep with libz ......... : ${enable_pcregrep_libz} + Link pcregrep with libbz2 ....... : ${enable_pcregrep_libbz2} + Link pcretest with libreadline .. : ${enable_pcretest_libreadline} -case $host_os in -mingw* ) - POSIX_OBJ=pcreposix.o - POSIX_LOBJ=pcreposix.lo - POSIX_LIB= - ON_WINDOWS= - NOT_ON_WINDOWS="#" - WIN_PREFIX= - ;; -* ) - ON_WINDOWS="#" - NOT_ON_WINDOWS= - POSIX_OBJ= - POSIX_LOBJ= - POSIX_LIB=libpcreposix.la - WIN_PREFIX= - ;; -esac -AC_SUBST(WIN_PREFIX) -AC_SUBST(ON_WINDOWS) -AC_SUBST(NOT_ON_WINDOWS) -AC_SUBST(POSIX_OBJ) -AC_SUBST(POSIX_LOBJ) -AC_SUBST(POSIX_LIB) - -if test "x$enable_shared" = "xno" ; then - AC_DEFINE([PCRE_STATIC],[1],[to link statically]) -fi +EOF -dnl This must be last; it determines what files are written as well as config.h -AC_OUTPUT(Makefile pcre-config:pcre-config.in libpcre.pc:libpcre.pc.in pcrecpparg.h:pcrecpparg.h.in pcre_stringpiece.h:pcre_stringpiece.h.in RunGrepTest:RunGrepTest.in RunTest:RunTest.in,[chmod a+x RunTest RunGrepTest pcre-config]) +dnl end configure.ac Added: freeswitch/trunk/libs/pcre/depcomp ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/depcomp Mon Jun 8 18:51:30 2009 @@ -0,0 +1,589 @@ +#! /bin/sh +# depcomp - compile a program generating dependencies as side-effects + +scriptversion=2007-03-29.01 + +# Copyright (C) 1999, 2000, 2003, 2004, 2005, 2006, 2007 Free Software +# Foundation, Inc. + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2, or (at your option) +# any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA +# 02110-1301, USA. + +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# Originally written by Alexandre Oliva <oliva@dcc.unicamp.br>. + +case $1 in + '') + echo "$0: No command. Try \`$0 --help' for more information." 1>&2 + exit 1; + ;; + -h | --h*) + cat <<\EOF +Usage: depcomp [--help] [--version] PROGRAM [ARGS] + +Run PROGRAMS ARGS to compile a file, generating dependencies +as side-effects. + +Environment variables: + depmode Dependency tracking mode. + source Source file read by `PROGRAMS ARGS'. + object Object file output by `PROGRAMS ARGS'. + DEPDIR directory where to store dependencies. + depfile Dependency file to output. + tmpdepfile Temporary file to use when outputing dependencies. + libtool Whether libtool is used (yes/no). + +Report bugs to <bug-automake@gnu.org>. +EOF + exit $? + ;; + -v | --v*) + echo "depcomp $scriptversion" + exit $? + ;; +esac + +if test -z "$depmode" || test -z "$source" || test -z "$object"; then + echo "depcomp: Variables source, object and depmode must be set" 1>&2 + exit 1 +fi + +# Dependencies for sub/bar.o or sub/bar.obj go into sub/.deps/bar.Po. +depfile=${depfile-`echo "$object" | + sed 's|[^\\/]*$|'${DEPDIR-.deps}'/&|;s|\.\([^.]*\)$|.P\1|;s|Pobj$|Po|'`} +tmpdepfile=${tmpdepfile-`echo "$depfile" | sed 's/\.\([^.]*\)$/.T\1/'`} + +rm -f "$tmpdepfile" + +# Some modes work just like other modes, but use different flags. We +# parameterize here, but still list the modes in the big case below, +# to make depend.m4 easier to write. Note that we *cannot* use a case +# here, because this file can only contain one case statement. +if test "$depmode" = hp; then + # HP compiler uses -M and no extra arg. + gccflag=-M + depmode=gcc +fi + +if test "$depmode" = dashXmstdout; then + # This is just like dashmstdout with a different argument. + dashmflag=-xM + depmode=dashmstdout +fi + +case "$depmode" in +gcc3) +## gcc 3 implements dependency tracking that does exactly what +## we want. Yay! Note: for some reason libtool 1.4 doesn't like +## it if -MD -MP comes after the -MF stuff. Hmm. +## Unfortunately, FreeBSD c89 acceptance of flags depends upon +## the command line argument order; so add the flags where they +## appear in depend2.am. Note that the slowdown incurred here +## affects only configure: in makefiles, %FASTDEP% shortcuts this. + for arg + do + case $arg in + -c) set fnord "$@" -MT "$object" -MD -MP -MF "$tmpdepfile" "$arg" ;; + *) set fnord "$@" "$arg" ;; + esac + shift # fnord + shift # $arg + done + "$@" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + mv "$tmpdepfile" "$depfile" + ;; + +gcc) +## There are various ways to get dependency output from gcc. Here's +## why we pick this rather obscure method: +## - Don't want to use -MD because we'd like the dependencies to end +## up in a subdir. Having to rename by hand is ugly. +## (We might end up doing this anyway to support other compilers.) +## - The DEPENDENCIES_OUTPUT environment variable makes gcc act like +## -MM, not -M (despite what the docs say). +## - Using -M directly means running the compiler twice (even worse +## than renaming). + if test -z "$gccflag"; then + gccflag=-MD, + fi + "$@" -Wp,"$gccflag$tmpdepfile" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + echo "$object : \\" > "$depfile" + alpha=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz +## The second -e expression handles DOS-style file names with drive letters. + sed -e 's/^[^:]*: / /' \ + -e 's/^['$alpha']:\/[^:]*: / /' < "$tmpdepfile" >> "$depfile" +## This next piece of magic avoids the `deleted header file' problem. +## The problem is that when a header file which appears in a .P file +## is deleted, the dependency causes make to die (because there is +## typically no way to rebuild the header). We avoid this by adding +## dummy dependencies for each header file. Too bad gcc doesn't do +## this for us directly. + tr ' ' ' +' < "$tmpdepfile" | +## Some versions of gcc put a space before the `:'. On the theory +## that the space means something, we add a space to the output as +## well. +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +hp) + # This case exists only to let depend.m4 do its work. It works by + # looking at the text of this script. This case will never be run, + # since it is checked for above. + exit 1 + ;; + +sgi) + if test "$libtool" = yes; then + "$@" "-Wp,-MDupdate,$tmpdepfile" + else + "$@" -MDupdate "$tmpdepfile" + fi + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + + if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files + echo "$object : \\" > "$depfile" + + # Clip off the initial element (the dependent). Don't try to be + # clever and replace this with sed code, as IRIX sed won't handle + # lines with more than a fixed number of characters (4096 in + # IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines; + # the IRIX cc adds comments like `#:fec' to the end of the + # dependency line. + tr ' ' ' +' < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' | \ + tr ' +' ' ' >> $depfile + echo >> $depfile + + # The second pass generates a dummy entry for each header file. + tr ' ' ' +' < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \ + >> $depfile + else + # The sourcefile does not contain any dependencies, so just + # store a dummy comment line, to avoid errors with the Makefile + # "include basename.Plo" scheme. + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +aix) + # The C for AIX Compiler uses -M and outputs the dependencies + # in a .u file. In older versions, this file always lives in the + # current directory. Also, the AIX compiler puts `$object:' at the + # start of each line; $object doesn't have directory information. + # Version 6 uses the directory in both cases. + dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` + test "x$dir" = "x$object" && dir= + base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` + if test "$libtool" = yes; then + tmpdepfile1=$dir$base.u + tmpdepfile2=$base.u + tmpdepfile3=$dir.libs/$base.u + "$@" -Wc,-M + else + tmpdepfile1=$dir$base.u + tmpdepfile2=$dir$base.u + tmpdepfile3=$dir$base.u + "$@" -M + fi + stat=$? + + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" + exit $stat + fi + + for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" + do + test -f "$tmpdepfile" && break + done + if test -f "$tmpdepfile"; then + # Each line is of the form `foo.o: dependent.h'. + # Do two passes, one to just change these to + # `$object: dependent.h' and one to simply `dependent.h:'. + sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile" + # That's a tab and a space in the []. + sed -e 's,^.*\.[a-z]*:[ ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile" + else + # The sourcefile does not contain any dependencies, so just + # store a dummy comment line, to avoid errors with the Makefile + # "include basename.Plo" scheme. + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +icc) + # Intel's C compiler understands `-MD -MF file'. However on + # icc -MD -MF foo.d -c -o sub/foo.o sub/foo.c + # ICC 7.0 will fill foo.d with something like + # foo.o: sub/foo.c + # foo.o: sub/foo.h + # which is wrong. We want: + # sub/foo.o: sub/foo.c + # sub/foo.o: sub/foo.h + # sub/foo.c: + # sub/foo.h: + # ICC 7.1 will output + # foo.o: sub/foo.c sub/foo.h + # and will wrap long lines using \ : + # foo.o: sub/foo.c ... \ + # sub/foo.h ... \ + # ... + + "$@" -MD -MF "$tmpdepfile" + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + # Each line is of the form `foo.o: dependent.h', + # or `foo.o: dep1.h dep2.h \', or ` dep3.h dep4.h \'. + # Do two passes, one to just change these to + # `$object: dependent.h' and one to simply `dependent.h:'. + sed "s,^[^:]*:,$object :," < "$tmpdepfile" > "$depfile" + # Some versions of the HPUX 10.20 sed can't process this invocation + # correctly. Breaking it into two sed invocations is a workaround. + sed 's,^[^:]*: \(.*\)$,\1,;s/^\\$//;/^$/d;/:$/d' < "$tmpdepfile" | + sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +hp2) + # The "hp" stanza above does not work with aCC (C++) and HP's ia64 + # compilers, which have integrated preprocessors. The correct option + # to use with these is +Maked; it writes dependencies to a file named + # 'foo.d', which lands next to the object file, wherever that + # happens to be. + # Much of this is similar to the tru64 case; see comments there. + dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` + test "x$dir" = "x$object" && dir= + base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` + if test "$libtool" = yes; then + tmpdepfile1=$dir$base.d + tmpdepfile2=$dir.libs/$base.d + "$@" -Wc,+Maked + else + tmpdepfile1=$dir$base.d + tmpdepfile2=$dir$base.d + "$@" +Maked + fi + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile1" "$tmpdepfile2" + exit $stat + fi + + for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" + do + test -f "$tmpdepfile" && break + done + if test -f "$tmpdepfile"; then + sed -e "s,^.*\.[a-z]*:,$object:," "$tmpdepfile" > "$depfile" + # Add `dependent.h:' lines. + sed -ne '2,${; s/^ *//; s/ \\*$//; s/$/:/; p;}' "$tmpdepfile" >> "$depfile" + else + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" "$tmpdepfile2" + ;; + +tru64) + # The Tru64 compiler uses -MD to generate dependencies as a side + # effect. `cc -MD -o foo.o ...' puts the dependencies into `foo.o.d'. + # At least on Alpha/Redhat 6.1, Compaq CCC V6.2-504 seems to put + # dependencies in `foo.d' instead, so we check for that too. + # Subdirectories are respected. + dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` + test "x$dir" = "x$object" && dir= + base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` + + if test "$libtool" = yes; then + # With Tru64 cc, shared objects can also be used to make a + # static library. This mechanism is used in libtool 1.4 series to + # handle both shared and static libraries in a single compilation. + # With libtool 1.4, dependencies were output in $dir.libs/$base.lo.d. + # + # With libtool 1.5 this exception was removed, and libtool now + # generates 2 separate objects for the 2 libraries. These two + # compilations output dependencies in $dir.libs/$base.o.d and + # in $dir$base.o.d. We have to check for both files, because + # one of the two compilations can be disabled. We should prefer + # $dir$base.o.d over $dir.libs/$base.o.d because the latter is + # automatically cleaned when .libs/ is deleted, while ignoring + # the former would cause a distcleancheck panic. + tmpdepfile1=$dir.libs/$base.lo.d # libtool 1.4 + tmpdepfile2=$dir$base.o.d # libtool 1.5 + tmpdepfile3=$dir.libs/$base.o.d # libtool 1.5 + tmpdepfile4=$dir.libs/$base.d # Compaq CCC V6.2-504 + "$@" -Wc,-MD + else + tmpdepfile1=$dir$base.o.d + tmpdepfile2=$dir$base.d + tmpdepfile3=$dir$base.d + tmpdepfile4=$dir$base.d + "$@" -MD + fi + + stat=$? + if test $stat -eq 0; then : + else + rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" + exit $stat + fi + + for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" + do + test -f "$tmpdepfile" && break + done + if test -f "$tmpdepfile"; then + sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile" + # That's a tab and a space in the []. + sed -e 's,^.*\.[a-z]*:[ ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile" + else + echo "#dummy" > "$depfile" + fi + rm -f "$tmpdepfile" + ;; + +#nosideeffect) + # This comment above is used by automake to tell side-effect + # dependency tracking mechanisms from slower ones. + +dashmstdout) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout, regardless of -o. + "$@" || exit $? + + # Remove the call to Libtool. + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + + # Remove `-o $object'. + IFS=" " + for arg + do + case $arg in + -o) + shift + ;; + $object) + shift + ;; + *) + set fnord "$@" "$arg" + shift # fnord + shift # $arg + ;; + esac + done + + test -z "$dashmflag" && dashmflag=-M + # Require at least two characters before searching for `:' + # in the target name. This is to cope with DOS-style filenames: + # a dependency such as `c:/foo/bar' could be seen as target `c' otherwise. + "$@" $dashmflag | + sed 's:^[ ]*[^: ][^:][^:]*\:[ ]*:'"$object"'\: :' > "$tmpdepfile" + rm -f "$depfile" + cat < "$tmpdepfile" > "$depfile" + tr ' ' ' +' < "$tmpdepfile" | \ +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +dashXmstdout) + # This case only exists to satisfy depend.m4. It is never actually + # run, as this mode is specially recognized in the preamble. + exit 1 + ;; + +makedepend) + "$@" || exit $? + # Remove any Libtool call + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + # X makedepend + shift + cleared=no + for arg in "$@"; do + case $cleared in + no) + set ""; shift + cleared=yes ;; + esac + case "$arg" in + -D*|-I*) + set fnord "$@" "$arg"; shift ;; + # Strip any option that makedepend may not understand. Remove + # the object too, otherwise makedepend will parse it as a source file. + -*|$object) + ;; + *) + set fnord "$@" "$arg"; shift ;; + esac + done + obj_suffix="`echo $object | sed 's/^.*\././'`" + touch "$tmpdepfile" + ${MAKEDEPEND-makedepend} -o"$obj_suffix" -f"$tmpdepfile" "$@" + rm -f "$depfile" + cat < "$tmpdepfile" > "$depfile" + sed '1,2d' "$tmpdepfile" | tr ' ' ' +' | \ +## Some versions of the HPUX 10.20 sed can't process this invocation +## correctly. Breaking it into two sed invocations is a workaround. + sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" "$tmpdepfile".bak + ;; + +cpp) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout. + "$@" || exit $? + + # Remove the call to Libtool. + if test "$libtool" = yes; then + while test $1 != '--mode=compile'; do + shift + done + shift + fi + + # Remove `-o $object'. + IFS=" " + for arg + do + case $arg in + -o) + shift + ;; + $object) + shift + ;; + *) + set fnord "$@" "$arg" + shift # fnord + shift # $arg + ;; + esac + done + + "$@" -E | + sed -n -e '/^# [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' \ + -e '/^#line [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' | + sed '$ s: \\$::' > "$tmpdepfile" + rm -f "$depfile" + echo "$object : \\" > "$depfile" + cat < "$tmpdepfile" >> "$depfile" + sed < "$tmpdepfile" '/^$/d;s/^ //;s/ \\$//;s/$/ :/' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +msvisualcpp) + # Important note: in order to support this mode, a compiler *must* + # always write the preprocessed file to stdout, regardless of -o, + # because we must use -o when running libtool. + "$@" || exit $? + IFS=" " + for arg + do + case "$arg" in + "-Gm"|"/Gm"|"-Gi"|"/Gi"|"-ZI"|"/ZI") + set fnord "$@" + shift + shift + ;; + *) + set fnord "$@" "$arg" + shift + shift + ;; + esac + done + "$@" -E | + sed -n '/^#line [0-9][0-9]* "\([^"]*\)"/ s::echo "`cygpath -u \\"\1\\"`":p' | sort | uniq > "$tmpdepfile" + rm -f "$depfile" + echo "$object : \\" > "$depfile" + . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s:: \1 \\:p' >> "$depfile" + echo " " >> "$depfile" + . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s::\1\::p' >> "$depfile" + rm -f "$tmpdepfile" + ;; + +none) + exec "$@" + ;; + +*) + echo "Unknown depmode $depmode" 1>&2 + exit 1 + ;; +esac + +exit 0 + +# Local Variables: +# mode: shell-script +# sh-indentation: 2 +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "scriptversion=" +# time-stamp-format: "%:y-%02m-%02d.%02H" +# time-stamp-end: "$" +# End: Modified: freeswitch/trunk/libs/pcre/dftables.c ============================================================================== --- freeswitch/trunk/libs/pcre/dftables.c (original) +++ freeswitch/trunk/libs/pcre/dftables.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -38,14 +38,19 @@ */ -/* This is a freestanding support program to generate a file containing default -character tables for PCRE. The tables are built according to the default C +/* This is a freestanding support program to generate a file containing +character tables for PCRE. The tables are built according to the current locale. Now that pcre_maketables is a function visible to the outside world, we make use of its code from here in order to be consistent. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <ctype.h> #include <stdio.h> #include <string.h> +#include <locale.h> #include "pcre_internal.h" @@ -55,38 +60,60 @@ int main(int argc, char **argv) { -int i; FILE *f; -const unsigned char *tables = pcre_maketables(); -const unsigned char *base_of_tables = tables; +int i = 1; +const unsigned char *tables; +const unsigned char *base_of_tables; + +/* By default, the default C locale is used rather than what the building user +happens to have set. However, if the -L option is given, set the locale from +the LC_xxx environment variables. */ -if (argc != 2) +if (argc > 1 && strcmp(argv[1], "-L") == 0) + { + setlocale(LC_ALL, ""); /* Set from environment variables */ + i++; + } + +if (argc < i + 1) { fprintf(stderr, "dftables: one filename argument is required\n"); return 1; } -f = fopen(argv[1], "wb"); +tables = pcre_maketables(); +base_of_tables = tables; + +f = fopen(argv[i], "wb"); if (f == NULL) { fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); return 1; } -/* There are two fprintf() calls here, because gcc in pedantic mode complains -about the very long string otherwise. */ +/* There are several fprintf() calls here, because gcc in pedantic mode +complains about the very long string otherwise. */ fprintf(f, "/*************************************************\n" "* Perl-Compatible Regular Expressions *\n" "*************************************************/\n\n" - "/* This file is automatically written by the dftables auxiliary \n" - "program. If you edit it by hand, you might like to edit the Makefile to \n" - "prevent its ever being regenerated.\n\n"); + "/* This file was automatically written by the dftables auxiliary\n" + "program. It contains character tables that are used when no external\n" + "tables are passed to PCRE by the application that calls it. The tables\n" + "are used only for characters whose code values are less than 256.\n\n"); +fprintf(f, + "The following #includes are present because without them gcc 4.x may remove\n" + "the array definition from the final binary if PCRE is built into a static\n" + "library and dead code stripping is activated. This leads to link errors.\n" + "Pulling in the header ensures that the array gets flagged as \"someone\n" + "outside this compilation unit might reference this\" and so it will always\n" + "be supplied to the linker. */\n\n" + "#ifdef HAVE_CONFIG_H\n" + "#include \"config.h\"\n" + "#endif\n\n" + "#include \"pcre_internal.h\"\n\n"); fprintf(f, - "This file contains the default tables for characters with codes less than\n" - "128 (ASCII characters). These tables are used when no external tables are\n" - "passed to PCRE. */\n\n" "const unsigned char _pcre_default_tables[] = {\n\n" "/* This table is a lower casing table. */\n\n"); @@ -162,7 +189,7 @@ else fprintf(f, "%3d-", i-8); if (isprint(i-1)) fprintf(f, " %c ", i-1); else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of chartables.c */\n"); +fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); fclose(f); free((void *)base_of_tables); Modified: freeswitch/trunk/libs/pcre/doc/html/index.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/index.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/index.html Mon Jun 8 18:51:30 2009 @@ -1,4 +1,10 @@ <html> +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are + created by the 132html script. +--> <head> <title>PCRE specification</title> </head> @@ -12,6 +18,9 @@ <tr><td><a href="pcre.html">pcre</a></td> <td>  Introductory page</td></tr> +<tr><td><a href="pcre-config.html">pcre-config</a></td> + <td>  Information about the installation configuration</td></tr> + <tr><td><a href="pcreapi.html">pcreapi</a></td> <td>  PCRE's native API</td></tr> @@ -54,6 +63,9 @@ <tr><td><a href="pcrestack.html">pcrestack</a></td> <td>  Discussion of PCRE's stack usage</td></tr> +<tr><td><a href="pcresyntax.html">pcresyntax</a></td> + <td>  Syntax quick-reference summary</td></tr> + <tr><td><a href="pcretest.html">pcretest</a></td> <td>  The <b>pcretest</b> command for testing PCRE</td></tr> </table> Added: freeswitch/trunk/libs/pcre/doc/html/pcre-config.html ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/html/pcre-config.html Mon Jun 8 18:51:30 2009 @@ -0,0 +1,88 @@ +<html> +<head> +<title>pcre-config specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre-config man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">OPTIONS</a> +<li><a name="TOC4" href="#SEC4">SEE ALSO</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>pcre-config [--prefix] [--exec-prefix] [--version] [--libs]</b> +<b>[--libs-posix] [--cflags] [--cflags-posix]</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +<b>pcre-config</b> returns the configuration of the installed PCRE +libraries and the options required to compile a program to use them. +</P> +<br><a name="SEC3" href="#TOC1">OPTIONS</a><br> +<P> +<b>--prefix</b> +Writes the directory prefix used in the PCRE installation for architecture +independent files (<i>/usr</i> on many systems, <i>/usr/local</i> on some +systems) to the standard output. +</P> +<P> +<b>--exec-prefix</b> +Writes the directory prefix used in the PCRE installation for architecture +dependent files (normally the same as <b>--prefix</b>) to the standard output. +</P> +<P> +<b>--version</b> +Writes the version number of the installed PCRE libraries to the standard +output. +</P> +<P> +<b>--libs</b> +Writes to the standard output the command line options required to link +with PCRE (<b>-lpcre</b> on many systems). +</P> +<P> +<b>--libs-posix</b> +Writes to the standard output the command line options required to link with +the PCRE posix emulation library (<b>-lpcreposix</b> <b>-lpcre</b> on many +systems). +</P> +<P> +<b>--cflags</b> +Writes to the standard output the command line options required to compile +files that use PCRE (this may include some <b>-I</b> options, but is blank on +many systems). +</P> +<P> +<b>--cflags-posix</b> +Writes to the standard output the command line options required to compile +files that use the PCRE posix emulation library (this may include some <b>-I</b> +options, but is blank on many systems). +</P> +<br><a name="SEC4" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcre(3)</b> +</P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> +<P> +This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been slightly revised as a generic PCRE man page. +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<P> +Last updated: 18 April 2007 +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre.html Mon Jun 8 18:51:30 2009 @@ -18,18 +18,26 @@ <li><a name="TOC3" href="#SEC3">LIMITATIONS</a> <li><a name="TOC4" href="#SEC4">UTF-8 AND UNICODE PROPERTY SUPPORT</a> <li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">INTRODUCTION</a><br> <P> The PCRE library is a set of functions that implement regular expression pattern matching using the same syntax and semantics as Perl, with just a few -differences. The current implementation of PCRE (release 6.x) corresponds -approximately with Perl 5.8, including support for UTF-8 encoded strings and -Unicode general category properties. However, this support has to be explicitly -enabled; it is not the default. +differences. Certain features that appeared in Python and PCRE before they +appeared in Perl are also available using the Python syntax. There is also some +support for certain .NET and Oniguruma syntax items, and there is an option for +requesting some minor changes that give better JavaScript compatibility. </P> <P> -In addition to the Perl-compatible matching function, PCRE also contains an +The current implementation of PCRE (release 7.x) corresponds approximately with +Perl 5.10, including support for UTF-8 encoded strings and Unicode general +category properties. However, UTF-8 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 5.1. +</P> +<P> +In addition to the Perl-compatible matching function, PCRE contains an alternative matching function that matches the same compiled patterns in a different way. In certain circumstances, the alternative function has some advantages. For a discussion of the two matching algorithms, see the @@ -52,7 +60,9 @@ <a href="pcrepattern.html"><b>pcrepattern</b></a> and <a href="pcrecompat.html"><b>pcrecompat</b></a> -pages. +pages. There is a syntax summary in the +<a href="pcresyntax.html"><b>pcresyntax</b></a> +page. </P> <P> Some features of PCRE can be included, excluded, or changed when the library is @@ -82,6 +92,7 @@ follows: <pre> pcre this document + pcre-config show PCRE installation configuration information pcreapi details of PCRE's native C API pcrebuild options for building PCRE pcrecallout details of the callout feature @@ -91,6 +102,7 @@ pcrematching discussion of the two matching algorithms pcrepartial details of the partial matching facility pcrepattern syntax and semantics of supported regular expressions + pcresyntax quick syntax reference pcreperform discussion of performance issues pcreposix the POSIX-compatible C API pcreprecompile details of saving and re-using precompiled patterns @@ -114,21 +126,18 @@ distribution and the <a href="pcrebuild.html"><b>pcrebuild</b></a> documentation for details). In these cases the limit is substantially larger. -However, the speed of execution will be slower. +However, the speed of execution is slower. </P> <P> -All values in repeating quantifiers must be less than 65536. The maximum -compiled length of subpattern with an explicit repeat count is 30000 bytes. The -maximum number of capturing subpatterns is 65535. +All values in repeating quantifiers must be less than 65536. </P> <P> -There is no limit to the number of non-capturing subpatterns, but the maximum -depth of nesting of all kinds of parenthesized subpattern, including capturing -subpatterns, assertions, and other types of subpattern, is 200. +There is no limit to the number of parenthesized subpatterns, but there can be +no more than 65535 capturing subpatterns. </P> <P> -The maximum length of name for a named subpattern is 32, and the maximum number -of named subpatterns is 10000. +The maximum length of name for a named subpattern is 32 characters, and the +maximum number of named subpatterns is 10000. </P> <P> The maximum length of a subject string is the largest positive number that an @@ -151,14 +160,15 @@ In order process UTF-8 strings, you must build PCRE to include UTF-8 support in the code, and, in addition, you must call <a href="pcre_compile.html"><b>pcre_compile()</b></a> -with the PCRE_UTF8 option flag. When you do this, both the pattern and any -subject strings that are matched against it are treated as UTF-8 strings -instead of just strings of bytes. +with the PCRE_UTF8 option flag, or the pattern must start with the sequence +(*UTF8). When either of these is the case, both the pattern and any subject +strings that are matched against it are treated as UTF-8 strings instead of +just strings of bytes. </P> <P> If you compile PCRE with UTF-8 support, but do not use it at run time, the library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag in several places, so should not be very large. +to testing the PCRE_UTF8 flag occasionally, so should not be very big. </P> <P> If PCRE is built with Unicode character property support (which implies UTF-8 @@ -172,56 +182,95 @@ \p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. Furthermore, in Perl, many properties may optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE does not support this. -</P> -<P> -The following comments apply when PCRE is running in UTF-8 mode: -</P> -<P> -1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are checked for validity on entry to the relevant functions. If an invalid -UTF-8 string is passed, an error return is given. In some situations, you may -already know that your strings are valid, and therefore want to skip these -checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag -at compile time or at run time, PCRE assumes that the pattern or subject it -is given (respectively) contains only valid UTF-8 codes. In this case, it does -not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to -PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program -may crash. -</P> +<a name="utf8strings"></a></P> +<br><b> +Validity of UTF-8 strings +</b><br> +<P> +When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects +are (by default) checked for validity on entry to the relevant functions. From +release 7.3 of PCRE, the check is according the rules of RFC 3629, which are +themselves derived from the Unicode specification. Earlier releases of PCRE +followed the rules of RFC 2279, which allows the full range of 31-bit values (0 +to 0x7FFFFFFF). The current check allows only values in the range U+0 to +U+10FFFF, excluding U+D800 to U+DFFF. +</P> +<P> +The excluded code points are the "Low Surrogate Area" of Unicode, of which the +Unicode Standard says this: "The Low Surrogate Area does not contain any +character assignments, consequently no character code charts or namelists are +provided for this area. Surrogates are reserved for use with UTF-16 and then +must be used in pairs." The code points that are encoded by UTF-16 pairs are +available as independent code points in the UTF-8 encoding. (In other words, +the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up +UTF-8.) +</P> +<P> +If an invalid UTF-8 string is passed to PCRE, an error return +(PCRE_ERROR_BADUTF8) is given. In some situations, you may already know that +your strings are valid, and therefore want to skip these checks in order to +improve performance. If you set the PCRE_NO_UTF8_CHECK flag at compile time or +at run time, PCRE assumes that the pattern or subject it is given +(respectively) contains only valid UTF-8 codes. In this case, it does not +diagnose an invalid UTF-8 string. +</P> +<P> +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, what +happens depends on why the string is invalid. If the string conforms to the +"old" definition of UTF-8 (RFC 2279), it is processed as a string of characters +in the range 0 to 0x7FFFFFFF. In other words, apart from the initial validity +test, PCRE (when in UTF-8 mode) handles strings according to the more liberal +rules of RFC 2279. However, if the string does not even conform to RFC 2279, +the result is undefined. Your program may crash. +</P> +<P> +If you want to process strings of values in the full range 0 to 0x7FFFFFFF, +encoded in a UTF-8-like manner as per the old RFC, you can set +PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in this +situation, you will have to apply your own validity check. +</P> +<br><b> +General comments about UTF-8 mode +</b><br> <P> -2. An unbraced hexadecimal escape sequence (such as \xb3) matches a two-byte +1. An unbraced hexadecimal escape sequence (such as \xb3) matches a two-byte UTF-8 character if the value is greater than 127. </P> <P> -3. Octal numbers up to \777 are recognized, and match two-byte UTF-8 +2. Octal numbers up to \777 are recognized, and match two-byte UTF-8 characters for values greater than \177. </P> <P> -4. Repeat quantifiers apply to complete UTF-8 characters, not to individual +3. Repeat quantifiers apply to complete UTF-8 characters, not to individual bytes, for example: \x{100}{3}. </P> <P> -5. The dot metacharacter matches one UTF-8 character instead of a single byte. +4. The dot metacharacter matches one UTF-8 character instead of a single byte. </P> <P> -6. The escape sequence \C can be used to match a single byte in UTF-8 mode, +5. The escape sequence \C can be used to match a single byte in UTF-8 mode, but its use can lead to some strange effects. This facility is not available in the alternative matching function, <b>pcre_dfa_exec()</b>. </P> <P> -7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly +6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test characters of any code value, but the characters that PCRE recognizes as digits, spaces, or word characters remain the same set as before, all with values less than 256. This remains true even when PCRE includes Unicode property support, because to do otherwise would slow down PCRE in many common cases. If you really want to test for a wider sense of, say, "digit", you -must use Unicode property tests such as \p{Nd}. +must use Unicode property tests such as \p{Nd}. Note that this also applies to +\b, because it is defined in terms of \w and \W. </P> <P> -8. Similarly, characters that match the POSIX named character classes are all +7. Similarly, characters that match the POSIX named character classes are all low-valued characters. </P> <P> +8. However, the Perl 5.10 horizontal and vertical whitespace matching escapes +(\h, \H, \v, and \V) do match all the appropriate Unicode characters. +</P> +<P> 9. Case-insensitive matching applies only to characters whose values are less than 128, unless PCRE is built with Unicode property support. Even when Unicode property support is available, PCRE still uses its own character tables when @@ -236,17 +285,22 @@ <P> Philip Hazel <br> -University Computing Service, +University Computing Service +<br> +Cambridge CB2 3QH, England. <br> -Cambridge CB2 3QG, England. </P> <P> Putting an actual email address here seems to have been a spam magnet, so I've -taken it away. If you want to email me, use my initial and surname, separated -by a dot, at the domain ucs.cam.ac.uk. -Last updated: 05 June 2006 +taken it away. If you want to email me, use my two initials, followed by the +two digits 10, at the domain cam.ac.uk. +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<P> +Last updated: 11 April 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_compile.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_compile.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_compile.html Mon Jun 8 18:51:30 2009 @@ -27,8 +27,9 @@ DESCRIPTION </b><br> <P> -This function compiles a regular expression into an internal form. Its -arguments are: +This function compiles a regular expression into an internal form. It is the +same as <b>pcre_compile2()</b>, except for the absence of the <i>errorcodeptr</i> +argument. Its arguments are: <pre> <i>pattern</i> A zero-terminated string containing the regular expression to be compiled @@ -40,34 +41,42 @@ </pre> The option bits are: <pre> - PCRE_ANCHORED Force pattern anchoring - PCRE_AUTO_CALLOUT Compile automatic callouts - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_DUPNAMES Allow duplicate names for subpatterns - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_FIRSTLINE Force matching to be before newline - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore whitespace and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF8 Run in UTF-8 mode + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) </pre> PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and PCRE_NO_UTF8_CHECK. </P> <P> The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_compile2.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_compile2.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_compile2.html Mon Jun 8 18:51:30 2009 @@ -56,6 +56,8 @@ (not much use currently) PCRE_FIRSTLINE Force matching to be before newline PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence @@ -72,7 +74,9 @@ </P> <P> The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_config.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_config.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_config.html Mon Jun 8 18:51:30 2009 @@ -38,7 +38,15 @@ PCRE_CONFIG_MATCH_LIMIT Internal resource limit PCRE_CONFIG_MATCH_LIMIT_RECURSION Internal recursion depth limit - PCRE_CONFIG_NEWLINE Value of the newline sequence + PCRE_CONFIG_NEWLINE Value of the default newline sequence: + 13 (0x000d) for CR + 10 (0x000a) for LF + 3338 (0x0d0a) for CRLF + -2 for ANYCRLF + -1 for ANY + PCRE_CONFIG_BSR Indicates what \R matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only PCRE_CONFIG_POSIX_MALLOC_THRESHOLD Threshold of return slots, above which <b>malloc()</b> is used by Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_copy_substring.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_copy_substring.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_copy_substring.html Mon Jun 8 18:51:30 2009 @@ -37,7 +37,7 @@ <i>buffer</i> Buffer to receive the string <i>buffersize</i> Size of buffer </pre> -The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was +The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. </P> <P> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_dfa_exec.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_dfa_exec.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_dfa_exec.html Mon Jun 8 18:51:30 2009 @@ -29,9 +29,9 @@ </b><br> <P> This function matches a compiled regular expression against a given subject -string, using a DFA matching algorithm (<i>not</i> Perl-compatible). Note that -the main, Perl-compatible, matching function is <b>pcre_exec()</b>. The -arguments for this function are: +string, using an alternative matching algorithm that scans the subject string +just once (<i>not</i> Perl-compatible). Note that the main, Perl-compatible, +matching function is <b>pcre_exec()</b>. The arguments for this function are: <pre> <i>code</i> Points to the compiled pattern <i>extra</i> Points to an associated <b>pcre_extra</b> structure, @@ -49,12 +49,17 @@ The options are: <pre> PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence PCRE_NOTBOL Subject is not the beginning of a line PCRE_NOTEOL Subject is not the end of a line PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) @@ -62,8 +67,8 @@ PCRE_DFA_SHORTEST Return only the shortest match PCRE_DFA_RESTART This is a restart after a partial match </pre> -There are restrictions on what may appear in a pattern when matching using the -DFA algorithm is requested. Details are given in the +There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the <a href="pcrematching.html"><b>pcrematching</b></a> documentation. </P> @@ -79,7 +84,7 @@ </pre> The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. For DFA matching, the <i>match_limit</i> and +PCRE_EXTRA_TABLES. For this matching function, the <i>match_limit</i> and <i>match_limit_recursion</i> fields are not used, and must not be set. </P> <P> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_exec.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_exec.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_exec.html Mon Jun 8 18:51:30 2009 @@ -45,19 +45,26 @@ The options are: <pre> PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence PCRE_NOTBOL Subject is not the beginning of a line PCRE_NOTEOL Subject is not the end of a line PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match </pre> There are restrictions on what may appear in a pattern when partial matching is -requested. +requested. For details, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +page. </P> <P> A <b>pcre_extra</b> structure contains the following fields: Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_fullinfo.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_fullinfo.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_fullinfo.html Mon Jun 8 18:51:30 2009 @@ -42,13 +42,14 @@ -1 for start of string or after newline, or -2 otherwise - PCRE_INFO_FIRSTTABLE Table of first bytes - (after studying) + PCRE_INFO_FIRSTTABLE Table of first bytes (after studying) + PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used PCRE_INFO_LASTLITERAL Literal last byte required PCRE_INFO_NAMECOUNT Number of named subpatterns PCRE_INFO_NAMEENTRYSIZE Size of name table entry PCRE_INFO_NAMETABLE Pointer to name table - PCRE_INFO_OPTIONS Options used for compilation + PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried + PCRE_INFO_OPTIONS Option bits used for compilation PCRE_INFO_SIZE Size of compiled pattern PCRE_INFO_STUDYSIZE Size of study data </pre> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_get_named_substring.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_get_named_substring.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_get_named_substring.html Mon Jun 8 18:51:30 2009 @@ -39,9 +39,10 @@ <i>stringptr</i> Where to put the string pointer </pre> The memory in which the substring is placed is obtained by calling -<b>pcre_malloc()</b>. The yield of the function is the length of the extracted -substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE_ERROR_NOSUBSTRING if the string name is invalid. +<b>pcre_malloc()</b>. The convenience function <b>pcre_free_substring()</b> can +be used to free it when it is no longer needed. The yield of the function is +the length of the extracted substring, PCRE_ERROR_NOMEMORY if sufficient memory +could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringnumber.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringnumber.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringnumber.html Mon Jun 8 18:51:30 2009 @@ -33,7 +33,10 @@ <i>name</i> Name whose number is required </pre> The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. +found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed +(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by +<b>pcre_get_stringnumber()</b>. You can obtain the complete list by calling +<b>pcre_get_stringtable_entries()</b>. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringtable_entries.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringtable_entries.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_get_stringtable_entries.html Mon Jun 8 18:51:30 2009 @@ -44,7 +44,7 @@ There is a complete description of the PCRE native API, including the format of the table entries, in the <a href="pcreapi.html"><b>pcreapi</b></a> -page and a description of the POSIX API in the +page, and a description of the POSIX API in the <a href="pcreposix.html"><b>pcreposix</b></a> page. <p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring.html Mon Jun 8 18:51:30 2009 @@ -37,9 +37,10 @@ <i>stringptr</i> Where to put the string pointer </pre> The memory in which the substring is placed is obtained by calling -<b>pcre_malloc()</b>. The yield of the function is the length of the substring, -PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE_ERROR_NOSUBSTRING if the string number is invalid. +<b>pcre_malloc()</b>. The convenience function <b>pcre_free_substring()</b> can +be used to free it when it is no longer needed. The yield of the function is +the length of the substring, PCRE_ERROR_NOMEMORY if sufficient memory could not +be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring_list.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring_list.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcre_get_substring_list.html Mon Jun 8 18:51:30 2009 @@ -35,10 +35,12 @@ <i>listptr</i> Where to put a pointer to the list </pre> The memory in which the substrings and the list are placed is obtained by -calling <b>pcre_malloc()</b>. A pointer to a list of pointers is put in -the variable whose address is in <i>listptr</i>. The list is terminated by a -NULL pointer. The yield of the function is zero on success or -PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained. +calling <b>pcre_malloc()</b>. The convenience function +<b>pcre_free_substring_list()</b> can be used to free it when it is no longer +needed. A pointer to a list of pointers is put in the variable whose address is +in <i>listptr</i>. The list is terminated by a NULL pointer. The yield of the +function is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could +not be obtained. </P> <P> There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/html/pcreapi.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcreapi.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcreapi.html Mon Jun 8 18:51:30 2009 @@ -32,6 +32,9 @@ <li><a name="TOC17" href="#SEC17">DUPLICATE SUBPATTERN NAMES</a> <li><a name="TOC18" href="#SEC18">FINDING ALL POSSIBLE MATCHES</a> <li><a name="TOC19" href="#SEC19">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a> +<li><a name="TOC20" href="#SEC20">SEE ALSO</a> +<li><a name="TOC21" href="#SEC21">AUTHOR</a> +<li><a name="TOC22" href="#SEC22">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE NATIVE API</a><br> <P> @@ -140,8 +143,8 @@ </P> <br><a name="SEC2" href="#TOC1">PCRE API OVERVIEW</a><br> <P> -PCRE has its own native API, which is described in this document. There is -also a set of wrapper functions that correspond to the POSIX regular expression +PCRE has its own native API, which is described in this document. There are +also some wrapper functions that correspond to the POSIX regular expression API. These are described in the <a href="pcreposix.html"><b>pcreposix</b></a> documentation. Both of these APIs define a set of C function calls. A C++ @@ -164,15 +167,15 @@ way of using them is provided in the file called <i>pcredemo.c</i> in the source distribution. The <a href="pcresample.html"><b>pcresample</b></a> -documentation describes how to run it. +documentation describes how to compile and run it. </P> <P> A second matching function, <b>pcre_dfa_exec()</b>, which is not Perl-compatible, is also provided. This uses a different algorithm for the matching. The alternative algorithm finds all possible matches (at a given -point in the subject). However, this algorithm does not return captured -substrings. A description of the two matching algorithms and their advantages -and disadvantages is given in the +point in the subject), and scans the subject just once. However, this algorithm +does not return captured substrings. A description of the two matching +algorithms and their advantages and disadvantages is given in the <a href="pcrematching.html"><b>pcrematching</b></a> documentation. </P> @@ -240,19 +243,45 @@ points during a matching operation. Details are given in the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. -</P> +<a name="newlines"></a></P> <br><a name="SEC3" href="#TOC1">NEWLINES</a><br> <P> -PCRE supports three different conventions for indicating line breaks in -strings: a single CR character, a single LF character, or the two-character -sequence CRLF. All three are used as "standard" by different operating systems. -When PCRE is built, a default can be specified. The default default is LF, -which is the Unix standard. When PCRE is run, the default can be overridden, -either when a pattern is compiled, or when it is matched. -<br> -<br> +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +</P> +<P> +Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE is built, a default can be specified. +The default default is LF, which is the Unix standard. When PCRE is run, the +default can be overridden, either when a pattern is compiled, or when it is +matched. +</P> +<P> +At compile time, the newline convention can be specified by the <i>options</i> +argument of <b>pcre_compile()</b>, or it can be specified by special text at the +start of the pattern itself; this overrides any other settings. See the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page for details of the special character sequences. +</P> +<P> In the PCRE documentation the word "newline" is used to mean "the character or -pair of characters that indicate a line break". +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +<a href="#execoptions">section on <b>pcre_exec()</b> options</a> +below. +</P> +<P> +The choice of newline convention does not affect the interpretation of +the \n or \r escape sequences, nor does it affect what \R matches, which is +controlled in a similar way, but by separate options. </P> <br><a name="SEC4" href="#TOC1">MULTITHREADING</a><br> <P> @@ -271,7 +300,9 @@ time, possibly by a different program, and even on a host other than the one on which it was compiled. Details are given in the <a href="pcreprecompile.html"><b>pcreprecompile</b></a> -documentation. +documentation. However, compiling a regular expression with one version of PCRE +for use with a different version is not guaranteed to work and may cause +crashes. </P> <br><a name="SEC6" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br> <P> @@ -301,9 +332,18 @@ PCRE_CONFIG_NEWLINE </pre> The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The three values that are supported -are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be -the standard sequence for your operating system. +that is recognized as meaning "newline". The four values that are supported +are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. +Though they are derived from ASCII, the same values are returned in EBCDIC +environments. The default should normally correspond to the standard sequence +for your operating system. +<pre> + PCRE_CONFIG_BSR +</pre> +The output is an integer whose value indicates what character sequences the \R +escape sequence matches by default. A value of 0 means that \R matches any +Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. <pre> PCRE_CONFIG_LINK_SIZE </pre> @@ -323,13 +363,13 @@ <pre> PCRE_CONFIG_MATCH_LIMIT </pre> -The output is an integer that gives the default limit for the number of +The output is a long integer that gives the default limit for the number of internal matching function calls in a <b>pcre_exec()</b> execution. Further details are given with <b>pcre_exec()</b> below. <pre> PCRE_CONFIG_MATCH_LIMIT_RECURSION </pre> -The output is an integer that gives the default limit for the depth of +The output is a long integer that gives the default limit for the depth of recursion when calling the internal matching function in a <b>pcre_exec()</b> execution. Further details are given with <b>pcre_exec()</b> below. <pre> @@ -374,16 +414,17 @@ argument, which is an address (see below). </P> <P> -The <i>options</i> argument contains independent bits that affect the +The <i>options</i> argument contains various bit settings that affect the compilation. It should be zero if no options are required. The available -options are described below. Some of them, in particular, those that are -compatible with Perl, can also be set and unset from within the pattern (see -the detailed description in the +options are described below. Some of them (in particular, those that are +compatible with Perl, but also some others) can also be set and unset from +within the pattern (see the detailed description in the <a href="pcrepattern.html"><b>pcrepattern</b></a> -documentation). For these options, the contents of the <i>options</i> argument -specifies their initial settings at the start of compilation and execution. The -PCRE_ANCHORED and PCRE_NEWLINE_<i>xxx</i> options can be set at the time of -matching as well as at compile time. +documentation). For those options that can be different in different parts of +the pattern, the contents of the <i>options</i> argument specifies their initial +settings at the start of compilation and execution. The PCRE_ANCHORED and +PCRE_NEWLINE_<i>xxx</i> options can be set at the time of matching as well as at +compile time. </P> <P> If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately. @@ -440,6 +481,15 @@ <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. <pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +<pre> PCRE_CASELESS </pre> If this bit is set, letters in the pattern match both upper and lower case @@ -467,8 +517,8 @@ including those that indicate newline. Without it, a dot does not match when the current position is at a newline. This option is equivalent to Perl's /s option, and it can be changed within a pattern by a (?s) option setting. A -negative class such as [^a] always matches newlines, independent of the setting -of this option. +negative class such as [^a] always matches newline characters, independent of +the setting of this option. <pre> PCRE_DUPNAMES </pre> @@ -511,6 +561,22 @@ the first newline in the subject string, though the matched text may continue over the newline. <pre> + PCRE_JAVASCRIPT_COMPAT +</pre> +If this option is set, PCRE's behaviour is changed in some ways so that it is +compatible with JavaScript rather than Perl. The changes are as follows: +</P> +<P> +(1) A lone closing square bracket in a pattern causes a compile-time error, +because this is illegal in JavaScript (by default it is treated as a data +character). Thus, the pattern AB]CD becomes illegal when this option is set. +</P> +<P> +(2) At run time, a back reference to an unset subpattern group matches an empty +string (by default this causes the current matching alternative to fail). A +pattern such as (\1)(a) succeeds when this option is set (assuming it can find +an "a" in the subject), whereas it fails by default, for Perl compatibility. +<pre> PCRE_MULTILINE </pre> By default, PCRE treats the subject string as consisting of a single line of @@ -531,19 +597,40 @@ PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY </pre> These options override the default newline definition that was chosen when PCRE was built. Setting the first or the second specifies that a newline is -indicated by a single character (CR or LF, respectively). Setting both of them -specifies that a newline is indicated by the two-character CRLF sequence. For -convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time -that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is -set, and an unescaped # outside a character class is encountered. This -indicates a comment that lasts until after the next newline. +indicated by a single character (CR or LF, respectively). Setting +PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character +CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three +preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies +that any Unicode newline sequence should be recognized. The Unicode newline +sequences are the three just mentioned, plus the single characters VT (vertical +tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line +separator, U+2028), and PS (paragraph separator, U+2029). The last two are +recognized only in UTF-8 mode. +</P> +<P> +The newline setting in the options word uses three bits that are treated +as a number, giving eight possibilities. Currently only six are used (default +plus the five values above). This means that if you set more than one newline +option, the combination may or may not be sensible. For example, +PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but +other combinations may yield unused numbers and cause an error. +</P> +<P> +The only time that a line break is specially recognized when compiling a +pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character +class is encountered. This indicates a comment that lasts until after the next +line break sequence. In other circumstances, line break sequences are treated +as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated +as whitespace characters and are therefore ignored. </P> <P> -The newline option set at compile time becomes the default that is used for -<b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden. +The newline option that is set at compile time becomes the default that is used +for <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden. <pre> PCRE_NO_AUTO_CAPTURE </pre> @@ -574,20 +661,24 @@ PCRE_NO_UTF8_CHECK </pre> When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. If an invalid UTF-8 sequence of bytes is found, -<b>pcre_compile()</b> returns an error. If you already know that your pattern is -valid, and you want to skip this check for performance reasons, you can set the -PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid -UTF-8 string as a pattern is undefined. It may cause your program to crash. -Note that this option can also be passed to <b>pcre_exec()</b> and -<b>pcre_dfa_exec()</b>, to suppress the UTF-8 validity checking of subject -strings. +automatically checked. There is a discussion about the +<a href="pcre.html#utf8strings">validity of UTF-8 strings</a> +in the main +<a href="pcre.html"><b>pcre</b></a> +page. If an invalid UTF-8 sequence of bytes is found, <b>pcre_compile()</b> +returns an error. If you already know that your pattern is valid, and you want +to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK +option. When it is set, the effect of passing an invalid UTF-8 string as a +pattern is undefined. It may cause your program to crash. Note that this option +can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress +the UTF-8 validity checking of subject strings. </P> <br><a name="SEC8" href="#TOC1">COMPILATION ERROR CODES</a><br> <P> The following table lists the error codes than may be returned by <b>pcre_compile2()</b>, along with the error messages that may be returned by -both compiling functions. +both compiling functions. As PCRE has developed, some error codes have fallen +out of use. To avoid confusion, they have not been re-used. <pre> 0 no error 1 \ at end of pattern @@ -599,17 +690,17 @@ 7 invalid escape sequence in character class 8 range out of order in character class 9 nothing to repeat - 10 operand of unlimited repeat could match the empty string + 10 [this code is not in use] 11 internal error: unexpected repeat - 12 unrecognized character after (? + 12 unrecognized character after (? or (?- 13 POSIX named classes are supported only within a class 14 missing ) 15 reference to non-existent subpattern 16 erroffset passed as NULL 17 unknown option bit(s) set 18 missing ) after comment - 19 parentheses nested too deeply - 20 regular expression too large + 19 [this code is not in use] + 20 regular expression is too large 21 failed to get memory 22 unmatched parentheses 23 internal error: code overflow @@ -618,11 +709,11 @@ 26 malformed number or name after (?( 27 conditional group contains more than two branches 28 assertion expected after (?( - 29 (?R or (?digits must be followed by ) + 29 (?R or (?[+-]digits must be followed by ) 30 unknown POSIX class name 31 POSIX collating elements are not supported 32 this version of PCRE is not compiled with PCRE_UTF8 support - 33 spare error + 33 [this code is not in use] 34 character value in \x{...} sequence is too large 35 invalid condition (?(0) 36 \C not allowed in lookbehind assertion @@ -631,17 +722,33 @@ 39 closing ) for (?C expected 40 recursive call could loop indefinitely 41 unrecognized character after (?P - 42 syntax error after (?P + 42 syntax error in subpattern name (missing terminator) 43 two named subpatterns have the same name 44 invalid UTF-8 string 45 support for \P, \p, and \X has not been compiled 46 malformed \P or \p sequence 47 unknown property name after \P or \p 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10,000) - 50 repeated subpattern is too long + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] 51 octal value is greater than \377 (not in UTF-8 mode) -</PRE> + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern not found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \g is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 (*VERB) with an argument is not supported + 60 (*VERB) not recognized + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode +</pre> +The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may +be used if the limits were changed when PCRE was built. </P> <br><a name="SEC9" href="#TOC1">STUDYING A PATTERN</a><br> <P> @@ -698,20 +805,27 @@ <a name="localesupport"></a></P> <br><a name="SEC10" href="#TOC1">LOCALE SUPPORT</a><br> <P> -PCRE handles caseless matching, and determines whether characters are letters +PCRE handles caseless matching, and determines whether characters are letters, digits, or whatever, by reference to a set of tables, indexed by character value. When running in UTF-8 mode, this applies only to characters with codes less than 128. Higher-valued codes never match escapes such as \w or \d, but can be tested with \p if PCRE is built with Unicode character property -support. The use of locales with Unicode is discouraged. -</P> -<P> -An internal set of tables is created in the default C locale when PCRE is -built. This is used when the final argument of <b>pcre_compile()</b> is NULL, -and is sufficient for many applications. An alternative set of tables can, -however, be supplied. These may be created in a different locale from the -default. As more and more applications change to using Unicode, the need for -this locale support is expected to die away. +support. The use of locales with Unicode is discouraged. If you are handling +characters with codes greater than 128, you should either use UTF-8 and +Unicode, or use locales, but not try to mix the two. +</P> +<P> +PCRE contains an internal set of tables that are used when the final argument +of <b>pcre_compile()</b> is NULL. These are sufficient for many applications. +Normally, the internal tables recognize only ASCII characters. However, when +PCRE is built, it is possible to cause the internal tables to be rebuilt in the +default "C" locale of the local system, which may cause them to be different. +</P> +<P> +The internal tables can always be overridden by tables supplied by the +application that calls PCRE. These may be created in a different locale from +the default. As more and more applications change to using Unicode, the need +for this locale support is expected to die away. </P> <P> External tables are built by calling the <b>pcre_maketables()</b> function, @@ -725,6 +839,10 @@ tables = pcre_maketables(); re = pcre_compile(..., tables); </pre> +The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". +</P> +<P> When <b>pcre_maketables()</b> runs, the tables are built in memory that is obtained via <b>pcre_malloc</b>. It is the caller's responsibility to ensure that the memory containing the tables remains available for as long as it is @@ -810,7 +928,7 @@ </P> <P> If there is a fixed first byte, for example, from a pattern such as -(cat|cow|coyote). Otherwise, if either +(cat|cow|coyote), its value is returned. Otherwise, if either <br> <br> (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch @@ -832,6 +950,18 @@ string, a pointer to the table is returned. Otherwise NULL is returned. The fourth argument should point to an <b>unsigned char *</b> variable. <pre> + PCRE_INFO_HASCRORLF +</pre> +Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The fourth argument should point to an <b>int</b> variable. An +explicit match is either a literal CR or LF character, or \r or \n. +<pre> + PCRE_INFO_JCHANGED +</pre> +Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The fourth argument should point to an <b>int</b> variable. (?J) and +(?-J) set and unset the local PCRE_DUPNAMES option, respectively. +<pre> PCRE_INFO_LASTLITERAL </pre> Return the value of the rightmost literal byte that must exist in any matched @@ -868,7 +998,7 @@ their parentheses numbers. For example, consider the following pattern (assume PCRE_EXTENDED is set, so white space - including newlines - is ignored): <pre> - (?P<date> (?P<year>(\d\d)?\d\d) - (?P<month>\d\d) - (?P<day>\d\d) ) + (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) </pre> There are four named subpatterns, so the table has four entries, and each entry in the table is eight bytes long. The table is as follows, with non-printing @@ -883,12 +1013,23 @@ name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. <pre> + PCRE_INFO_OKPARTIAL +</pre> +Return 1 if the pattern can be used for partial matching, otherwise 0. The +fourth argument should point to an <b>int</b> variable. The +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation lists the restrictions that apply to patterns when partial +matching is used. +<pre> PCRE_INFO_OPTIONS </pre> Return a copy of the options with which the pattern was compiled. The fourth argument should point to an <b>unsigned long int</b> variable. These option bits are those specified in the call to <b>pcre_compile()</b>, modified by any -top-level option settings within the pattern itself. +top-level option settings at the start of the pattern itself. In other words, +they are the options that will be in force when matching starts. For example, +if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the +result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. </P> <P> A pattern is automatically anchored by PCRE if all of its top-level @@ -1097,14 +1238,15 @@ called. See the <a href="pcreprecompile.html"><b>pcreprecompile</b></a> documentation for a discussion of saving compiled patterns for later use. -</P> +<a name="execoptions"></a></P> <br><b> Option bits for <b>pcre_exec()</b> </b><br> <P> The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, +PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. <pre> PCRE_ANCHORED </pre> @@ -1113,14 +1255,51 @@ to be anchored by virtue of its contents, it cannot be made unachored at matching time. <pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +<pre> PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY </pre> These options override the newline definition that was chosen or defaulted when -the pattern was compiled. For details, see the description <b>pcre_compile()</b> -above. During matching, the newline choice affects the behaviour of the dot, -circumflex, and dollar metacharacters. +the pattern was compiled. For details, see the description of +<b>pcre_compile()</b> above. During matching, the newline choice affects the +behaviour of the dot, circumflex, and dollar metacharacters. It may also alter +the way the match position is advanced after a match failure for an unanchored +pattern. +</P> +<P> +When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a +match attempt for an unanchored pattern fails when the current position is at a +CRLF sequence, and the pattern contains no explicit matches for CR or LF +characters, the match position is advanced by two characters instead of one, in +other words, to after the CRLF. +</P> +<P> +The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not +set), it does not match the string "\r\nA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\r\n]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +</P> +<P> +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \r or \n escape sequences. Implicit matches such as +[^X] do not count, nor does \s (which includes CR and LF in the characters +that it matches). +</P> +<P> +Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \r or \n escapes appear in the pattern. <pre> PCRE_NOTBOL </pre> @@ -1159,14 +1338,29 @@ starting offset (see below) and trying an ordinary match again. There is some code that demonstrates how to do this in the <i>pcredemo.c</i> sample program. <pre> + PCRE_NO_START_OPTIMIZE +</pre> +There are a number of optimizations that <b>pcre_exec()</b> uses at the start of +a match, in order to speed up the process. For example, if it is known that a +match must start with a specific character, it searches the subject for that +character, and fails immediately if it cannot find it, without actually running +the main matching function. When callouts are in use, these optimizations can +cause them to be skipped. This option disables the "start-up" optimizations, +causing performance to suffer, but ensuring that the callouts do occur. +<pre> PCRE_NO_UTF8_CHECK </pre> When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 string is automatically checked when <b>pcre_exec()</b> is subsequently called. The value of <i>startoffset</i> is also checked to ensure that it points to the -start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found, -<b>pcre_exec()</b> returns the error PCRE_ERROR_BADUTF8. If <i>startoffset</i> -contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. +start of a UTF-8 character. There is a discussion about the validity of UTF-8 +strings in the +<a href="pcre.html#utf8strings">section on UTF-8 support</a> +in the main +<a href="pcre.html"><b>pcre</b></a> +page. If an invalid UTF-8 sequence of bytes is found, <b>pcre_exec()</b> returns +the error PCRE_ERROR_BADUTF8. If <i>startoffset</i> contains an invalid value, +PCRE_ERROR_BADUTF8_OFFSET is returned. </P> <P> If you already know that your subject is valid, and you want to skip these @@ -1196,11 +1390,11 @@ </b><br> <P> The subject string is passed to <b>pcre_exec()</b> as a pointer in -<i>subject</i>, a length in <i>length</i>, and a starting byte offset in -<i>startoffset</i>. In UTF-8 mode, the byte offset must point to the start of a -UTF-8 character. Unlike the pattern string, the subject may contain binary zero -bytes. When the starting offset is zero, the search for a match starts at the -beginning of the subject, and this is by far the most common case. +<i>subject</i>, a length (in bytes) in <i>length</i>, and a starting byte offset +in <i>startoffset</i>. In UTF-8 mode, the byte offset must point to the start of +a UTF-8 character. Unlike the pattern string, the subject may contain binary +zero bytes. When the starting offset is zero, the search for a match starts at +the beginning of the subject, and this is by far the most common case. </P> <P> A non-zero starting offset is useful when searching for another match in the @@ -1238,32 +1432,36 @@ kinds of parenthesized subpattern that do not cause substrings to be captured. </P> <P> -Captured substrings are returned to the caller via a vector of integer offsets -whose address is passed in <i>ovector</i>. The number of elements in the vector -is passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: -this argument is NOT the size of <i>ovector</i> in bytes. +Captured substrings are returned to the caller via a vector of integers whose +address is passed in <i>ovector</i>. The number of elements in the vector is +passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: this +argument is NOT the size of <i>ovector</i> in bytes. </P> <P> The first two-thirds of the vector is used to pass back captured substrings, each substring using a pair of integers. The remaining third of the vector is used as workspace by <b>pcre_exec()</b> while matching capturing subpatterns, -and is not available for passing back information. The length passed in +and is not available for passing back information. The number passed in <i>ovecsize</i> should always be a multiple of three. If it is not, it is rounded down. </P> <P> When a match is successful, information about captured substrings is returned in pairs of integers, starting at the beginning of <i>ovector</i>, and -continuing up to two-thirds of its length at the most. The first element of a -pair is set to the offset of the first character in a substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by <b>pcre_exec()</b> -is one more than the highest numbered pair that has been set. For example, if -two substrings have been captured, the returned value is 3. If there are no -capturing subpatterns, the return value from a successful match is 1, -indicating that just the first pair of offsets has been set. +continuing up to two-thirds of its length at the most. The first element of +each pair is set to the byte offset of the first character in a substring, and +the second is set to the byte offset of the first character after the end of a +substring. <b>Note</b>: these values are always byte offsets, even in UTF-8 +mode. They are not character counts. +</P> +<P> +The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the +portion of the subject string matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +<b>pcre_exec()</b> is one more than the highest numbered pair that has been set. +For example, if two substrings have been captured, the returned value is 3. If +there are no capturing subpatterns, the return value from a successful match is +1, indicating that just the first pair of offsets has been set. </P> <P> If a capturing subpattern is matched repeatedly, it is the last portion of the @@ -1272,8 +1470,8 @@ <P> If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the function -returns a value of zero. In particular, if the substring offsets are not of -interest, <b>pcre_exec()</b> may be called with <i>ovector</i> passed as NULL and +returns a value of zero. If the substring offsets are not of interest, +<b>pcre_exec()</b> may be called with <i>ovector</i> passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains back references and the <i>ovector</i> is not big enough to remember the related substrings, PCRE has to get additional memory for use during matching. Thus it is usually @@ -1334,7 +1532,7 @@ other endianness. This is the error that PCRE gives when the magic number is not present. <pre> - PCRE_ERROR_UNKNOWN_NODE (-5) + PCRE_ERROR_UNKNOWN_OPCODE (-5) </pre> While running the pattern match, an unknown item was encountered in the compiled pattern. This error could be caused by a bug in PCRE or by overwriting @@ -1360,12 +1558,6 @@ <b>pcre_extra</b> structure (or defaulted) was reached. See the description above. <pre> - PCRE_ERROR_RECURSIONLIMIT (-21) -</pre> -The internal recursion limit, as specified by the <i>match_limit_recursion</i> -field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the -description above. -<pre> PCRE_ERROR_CALLOUT (-9) </pre> This error is never generated by <b>pcre_exec()</b> itself. It is provided for @@ -1403,6 +1595,19 @@ PCRE_ERROR_BADCOUNT (-15) </pre> This error is given if the value of the <i>ovecsize</i> argument is negative. +<pre> + PCRE_ERROR_RECURSIONLIMIT (-21) +</pre> +The internal recursion limit, as specified by the <i>match_limit_recursion</i> +field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the +description above. +<pre> + PCRE_ERROR_BADNEWLINE (-23) +</pre> +An invalid combination of PCRE_NEWLINE_<i>xxx</i> options was given. +</P> +<P> +Error numbers -16 to -20 and -22 are not used by <b>pcre_exec()</b>. </P> <br><a name="SEC15" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br> <P> @@ -1457,7 +1662,7 @@ <i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is obtained via <b>pcre_malloc</b>, and its address is returned via <i>stringptr</i>. The yield of the function is the length of the string, not -including the terminating zero, or one of +including the terminating zero, or one of these error codes: <pre> PCRE_ERROR_NOMEMORY (-6) </pre> @@ -1474,7 +1679,7 @@ memory that is obtained via <b>pcre_malloc</b>. The address of the memory block is returned via <i>listptr</i>, which is also the start of the list of string pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or +function is zero if all went well, or the error code <pre> PCRE_ERROR_NOMEMORY (-6) </pre> @@ -1520,7 +1725,7 @@ To extract a substring by name, you first have to find associated number. For example, for this pattern <pre> - (a+)b(?P<xxx>\d+)... + (a+)b(?<xxx>\d+)... </pre> the number of the subpattern called "xxx" is 2. If the name is known to be unique (PCRE_DUPNAMES was not set), you can find the number from the name by @@ -1548,8 +1753,15 @@ </P> <P> These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they -then call <i>pcre_copy_substring()</i> or <i>pcre_get_substring()</i>, as -appropriate. +then call <b>pcre_copy_substring()</b> or <b>pcre_get_substring()</b>, as +appropriate. <b>NOTE:</b> If PCRE_DUPNAMES is set and there are duplicate names, +the behaviour may not be what you want (see the next section). +</P> +<P> +<b>Warning:</b> If the pattern uses the "(?|" feature to set up multiple +subpatterns with the same number, you cannot use names to distinguish them, +because names are not included in the compiled code. The matching process uses +only numbers. </P> <br><a name="SEC17" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br> <P> @@ -1562,23 +1774,27 @@ that in any one match, only one of the named subpatterns participates. An example is shown in the <a href="pcrepattern.html"><b>pcrepattern</b></a> -documentation. When duplicates are present, <b>pcre_copy_named_substring()</b> -and <b>pcre_get_named_substring()</b> return the first substring corresponding -to the given name that is set. If none are set, an empty string is returned. -The <b>pcre_get_stringnumber()</b> function returns one of the numbers that are -associated with the name, but it is not defined which it is. -<br> -<br> +documentation. +</P> +<P> +When duplicates are present, <b>pcre_copy_named_substring()</b> and +<b>pcre_get_named_substring()</b> return the first substring corresponding to +the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is +returned; no data is returned. The <b>pcre_get_stringnumber()</b> function +returns one of the numbers that are associated with the name, but it is not +defined which it is. +</P> +<P> If you want to get full details of all captured substrings for a given name, you must use the <b>pcre_get_stringtable_entries()</b> function. The first argument is the compiled pattern, and the second is the name. The third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the given name. The function itself returns the length of each entry, or -PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described -above in the section entitled <i>Information about a pattern</i>. Given all the -relevant entries for the name, you can extract each of their numbers, and hence -the captured data, if any. +PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is +described above in the section entitled <i>Information about a pattern</i>. +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data, if any. </P> <br><a name="SEC18" href="#TOC1">FINDING ALL POSSIBLE MATCHES</a><br> <P> @@ -1608,11 +1824,12 @@ </P> <P> The function <b>pcre_dfa_exec()</b> is called to match a subject string against -a compiled pattern, using a "DFA" matching algorithm. This has different -characteristics to the normal algorithm, and is not compatible with Perl. Some -of the features of PCRE patterns are not supported. Nevertheless, there are -times when this kind of matching can be useful. For a discussion of the two -matching algorithms, see the +a compiled pattern, using a matching algorithm that scans the subject string +just once, and does not backtrack. This has different characteristics to the +normal algorithm, and is not compatible with Perl. Some of the features of PCRE +patterns are not supported. Nevertheless, there are times when this kind of +matching can be useful. For a discussion of the two matching algorithms, see +the <a href="pcrematching.html"><b>pcrematching</b></a> documentation. </P> @@ -1671,9 +1888,9 @@ PCRE_DFA_SHORTEST </pre> Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as -soon as it has found one match. Because of the way the DFA algorithm works, -this is necessarily the shortest possible match at the first possible matching -point in the subject string. +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. <pre> PCRE_DFA_RESTART </pre> @@ -1711,10 +1928,10 @@ On success, the yield of the function is a number greater than zero, which is the number of matched substrings. The substrings themselves are returned in <i>ovector</i>. Each string uses two elements; the first is the offset to the -start, and the second is the offset to the end. All the strings have the same -start offset. (Space could have been saved by giving this only once, but it was -decided to retain some compatibility with the way <b>pcre_exec()</b> returns -data, even though the meaning of the strings is different.) +start, and the second is the offset to the end. In fact, all the strings have +the same start offset. (Space could have been saved by giving this only once, +but it was decided to retain some compatibility with the way <b>pcre_exec()</b> +returns data, even though the meaning of the strings is different.) </P> <P> The strings are returned in reverse order of length; that is, the longest @@ -1740,8 +1957,9 @@ <pre> PCRE_ERROR_DFA_UCOND (-17) </pre> -This return is given if <b>pcre_dfa_exec()</b> encounters a condition item in a -pattern that uses a back reference for the condition. This is not supported. +This return is given if <b>pcre_dfa_exec()</b> encounters a condition item that +uses a back reference for the condition, or a test for recursion in a specific +group. These are not supported. <pre> PCRE_ERROR_DFA_UMLIMIT (-18) </pre> @@ -1761,10 +1979,27 @@ error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. </P> +<br><a name="SEC20" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcrebuild</b>(3), <b>pcrecallout</b>(3), <b>pcrecpp(3)</b>(3), +<b>pcrematching</b>(3), <b>pcrepartial</b>(3), <b>pcreposix</b>(3), +<b>pcreprecompile</b>(3), <b>pcresample</b>(3), <b>pcrestack</b>(3). +</P> +<br><a name="SEC21" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC22" href="#TOC1">REVISION</a><br> <P> -Last updated: 08 June 2006 +Last updated: 11 April 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrebuild.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrebuild.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrebuild.html Mon Jun 8 18:51:30 2009 @@ -18,26 +18,39 @@ <li><a name="TOC3" href="#SEC3">UTF-8 SUPPORT</a> <li><a name="TOC4" href="#SEC4">UNICODE CHARACTER PROPERTY SUPPORT</a> <li><a name="TOC5" href="#SEC5">CODE VALUE OF NEWLINE</a> -<li><a name="TOC6" href="#SEC6">BUILDING SHARED AND STATIC LIBRARIES</a> -<li><a name="TOC7" href="#SEC7">POSIX MALLOC USAGE</a> -<li><a name="TOC8" href="#SEC8">HANDLING VERY LARGE PATTERNS</a> -<li><a name="TOC9" href="#SEC9">AVOIDING EXCESSIVE STACK USAGE</a> -<li><a name="TOC10" href="#SEC10">LIMITING PCRE RESOURCE USAGE</a> -<li><a name="TOC11" href="#SEC11">USING EBCDIC CODE</a> +<li><a name="TOC6" href="#SEC6">WHAT \R MATCHES</a> +<li><a name="TOC7" href="#SEC7">BUILDING SHARED AND STATIC LIBRARIES</a> +<li><a name="TOC8" href="#SEC8">POSIX MALLOC USAGE</a> +<li><a name="TOC9" href="#SEC9">HANDLING VERY LARGE PATTERNS</a> +<li><a name="TOC10" href="#SEC10">AVOIDING EXCESSIVE STACK USAGE</a> +<li><a name="TOC11" href="#SEC11">LIMITING PCRE RESOURCE USAGE</a> +<li><a name="TOC12" href="#SEC12">CREATING CHARACTER TABLES AT BUILD TIME</a> +<li><a name="TOC13" href="#SEC13">USING EBCDIC CODE</a> +<li><a name="TOC14" href="#SEC14">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a> +<li><a name="TOC15" href="#SEC15">PCRETEST OPTION FOR LIBREADLINE SUPPORT</a> +<li><a name="TOC16" href="#SEC16">SEE ALSO</a> +<li><a name="TOC17" href="#SEC17">AUTHOR</a> +<li><a name="TOC18" href="#SEC18">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE BUILD-TIME OPTIONS</a><br> <P> This document describes the optional features of PCRE that can be selected when -the library is compiled. They are all selected, or deselected, by providing -options to the <b>configure</b> script that is run before the <b>make</b> -command. The complete list of options for <b>configure</b> (which includes the -standard ones such as the selection of the installation directory) can be -obtained by running +the library is compiled. It assumes use of the <b>configure</b> script, where +the optional features are selected or deselected by providing options to +<b>configure</b> before running the <b>make</b> command. However, the same +options can be selected in both Unix-like and non-Unix-like environments using +the GUI facility of <b>CMakeSetup</b> if you are using <b>CMake</b> instead of +<b>configure</b> to build PCRE. +</P> +<P> +The complete list of options for <b>configure</b> (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running <pre> ./configure --help </pre> -The following sections describe certain options whose names begin with --enable -or --disable. These settings specify changes to the defaults for the +The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the <b>configure</b> command. Because of the way that <b>configure</b> works, --enable and --disable always come in pairs, so the complementary option always exists as well, but as it specifies the default, it is not described. @@ -54,7 +67,7 @@ </P> <br><a name="SEC3" href="#TOC1">UTF-8 SUPPORT</a><br> <P> -To build PCRE with support for UTF-8 character strings, add +To build PCRE with support for UTF-8 Unicode character strings, add <pre> --enable-utf8 </pre> @@ -63,6 +76,13 @@ have to set the PCRE_UTF8 option when you call the <b>pcre_compile()</b> function. </P> +<P> +If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE expects +its input to be either ASCII or UTF-8 (depending on the runtime option). It is +not possible to support both EBCDIC and UTF-8 codes in the same version of the +library. Consequently, --enable-utf8 and --enable-ebcdic are mutually +exclusive. +</P> <br><a name="SEC4" href="#TOC1">UNICODE CHARACTER PROPERTY SUPPORT</a><br> <P> UTF-8 support allows PCRE to process character values greater than 255 in the @@ -77,17 +97,17 @@ not explicitly requested it. </P> <P> -Including Unicode property support adds around 90K of tables to the PCRE -library, approximately doubling its size. Only the general category properties -such as <i>Lu</i> and <i>Nd</i> are supported. Details are given in the +Including Unicode property support adds around 30K of tables to the PCRE +library. Only the general category properties such as <i>Lu</i> and <i>Nd</i> are +supported. Details are given in the <a href="pcrepattern.html"><b>pcrepattern</b></a> documentation. </P> <br><a name="SEC5" href="#TOC1">CODE VALUE OF NEWLINE</a><br> <P> -By default, PCRE interprets character 10 (linefeed, LF) as indicating the end +By default, PCRE interprets the linefeed (LF) character as indicating the end of a line. This is the normal newline character on Unix-like systems. You can -compile PCRE to use character 13 (carriage return, CR) instead, by adding +compile PCRE to use carriage return (CR) instead, by adding <pre> --enable-newline-is-cr </pre> @@ -100,11 +120,34 @@ <pre> --enable-newline-is-crlf </pre> -to the <b>configure</b> command. Whatever line ending convention is selected -when PCRE is built can be overridden when the library functions are called. At -build time it is conventional to use the standard for your operating system. +to the <b>configure</b> command. There is a fourth option, specified by +<pre> + --enable-newline-is-anycrlf +</pre> +which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +<pre> + --enable-newline-is-any +</pre> +causes PCRE to recognize any Unicode newline sequence. +</P> +<P> +Whatever line ending convention is selected when PCRE is built can be +overridden when the library functions are called. At build time it is +conventional to use the standard for your operating system. +</P> +<br><a name="SEC6" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +By default, the sequence \R in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +<pre> + --enable-bsr-anycrlf +</pre> +the default is changed so that \R matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. </P> -<br><a name="SEC6" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> +<br><a name="SEC7" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> <P> The PCRE building process uses <b>libtool</b> to build both shared and static Unix libraries by default. You can suppress one of these by adding one of @@ -114,7 +157,7 @@ </pre> to the <b>configure</b> command, as required. </P> -<br><a name="SEC7" href="#TOC1">POSIX MALLOC USAGE</a><br> +<br><a name="SEC8" href="#TOC1">POSIX MALLOC USAGE</a><br> <P> When PCRE is called through the POSIX interface (see the <a href="pcreposix.html"><b>pcreposix</b></a> @@ -130,7 +173,7 @@ </pre> to the <b>configure</b> command. </P> -<br><a name="SEC8" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> +<br><a name="SEC9" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> <P> Within a compiled pattern, offset values are used to point from one part to another (for example, from an opening parenthesis to an alternation @@ -146,12 +189,7 @@ longer offsets slows down the operation of PCRE because it has to load additional bytes when handling them. </P> -<P> -If you build PCRE with an increased link size, test 2 (and test 5 if you are -using UTF-8) will fail. Part of the output of these tests is a representation -of the compiled pattern, and this changes with the link size. -</P> -<br><a name="SEC9" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> +<br><a name="SEC10" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> <P> When matching with the <b>pcre_exec()</b> function, PCRE implements backtracking by making recursive calls to an internal function called <b>match()</b>. In @@ -169,15 +207,20 @@ </pre> to the <b>configure</b> command. With this configuration, PCRE will use the <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> variables to call memory -management functions. Separate functions are provided because the usage is very -predictable: the block sizes requested are always the same, and the blocks are -always freed in reverse order. A calling program might be able to implement -optimized functions that perform better than the standard <b>malloc()</b> and -<b>free()</b> functions. PCRE runs noticeably more slowly when built in this -way. This option affects only the <b>pcre_exec()</b> function; it is not -relevant for the the <b>pcre_dfa_exec()</b> function. +management functions. By default these point to <b>malloc()</b> and +<b>free()</b>, but you can replace the pointers so that your own functions are +used. </P> -<br><a name="SEC10" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> +<P> +Separate functions are provided rather than using <b>pcre_malloc</b> and +<b>pcre_free</b> because the usage is very predictable: the block sizes +requested are always the same, and the blocks are always freed in reverse +order. A calling program might be able to implement optimized functions that +perform better than <b>malloc()</b> and <b>free()</b>. PCRE runs noticeably more +slowly when built in this way. This option affects only the <b>pcre_exec()</b> +function; it is not relevant for the the <b>pcre_dfa_exec()</b> function. +</P> +<br><a name="SEC11" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> <P> Internally, PCRE has a function called <b>match()</b>, which it calls repeatedly (sometimes recursively) when matching a pattern with the <b>pcre_exec()</b> @@ -206,20 +249,100 @@ </pre> to the <b>configure</b> command. This value can also be overridden at run time. </P> -<br><a name="SEC11" href="#TOC1">USING EBCDIC CODE</a><br> +<br><a name="SEC12" href="#TOC1">CREATING CHARACTER TABLES AT BUILD TIME</a><br> +<P> +PCRE uses fixed tables for processing characters whose code values are less +than 256. By default, PCRE is built with a set of tables that are distributed +in the file <i>pcre_chartables.c.dist</i>. These tables are for ASCII codes +only. If you add +<pre> + --enable-rebuild-chartables +</pre> +to the <b>configure</b> command, the distributed tables are no longer used. +Instead, a program called <b>dftables</b> is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C runtime +system. (This method of replacing the tables does not work if you are cross +compiling, because <b>dftables</b> is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) +</P> +<br><a name="SEC13" href="#TOC1">USING EBCDIC CODE</a><br> <P> PCRE assumes by default that it will run in an environment where the character -code is ASCII (or Unicode, which is a superset of ASCII). PCRE can, however, be -compiled to run in an EBCDIC environment by adding +code is ASCII (or Unicode, which is a superset of ASCII). This is the case for +most computer operating systems. PCRE can, however, be compiled to run in an +EBCDIC environment by adding <pre> --enable-ebcdic </pre> -to the <b>configure</b> command. +to the <b>configure</b> command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). The +--enable-ebcdic option is incompatible with --enable-utf8. </P> +<br><a name="SEC14" href="#TOC1">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a><br> <P> -Last updated: 06 June 2006 +By default, <b>pcregrep</b> reads all files as plain text. You can build it so +that it recognizes files whose names end in <b>.gz</b> or <b>.bz2</b>, and reads +them with <b>libz</b> or <b>libbz2</b>, respectively, by adding one or both of +<pre> + --enable-pcregrep-libz + --enable-pcregrep-libbz2 +</pre> +to the <b>configure</b> command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. +</P> +<br><a name="SEC15" href="#TOC1">PCRETEST OPTION FOR LIBREADLINE SUPPORT</a><br> +<P> +If you add +<pre> + --enable-pcretest-libreadline +</pre> +to the <b>configure</b> command, <b>pcretest</b> is linked with the +<b>libreadline</b> library, and when its input is from a terminal, it reads it +using the <b>readline()</b> function. This provides line-editing and history +facilities. Note that <b>libreadline</b> is GPL-licenced, so if you distribute a +binary of <b>pcretest</b> linked in this way, there may be licensing issues. +</P> +<P> +Setting this option causes the <b>-lreadline</b> option to be added to the +<b>pcretest</b> build. In many operating environments with a sytem-installed +<b>libreadline</b> this is sufficient. However, in some environments (e.g. +if an unmodified distribution version of readline is in use), some extra +configuration may be necessary. The INSTALL file for <b>libreadline</b> says +this: +<pre> + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." +</pre> +If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +<pre> + LIBS="-ncurses" +</pre> +immediately before the <b>configure</b> command. +</P> +<br><a name="SEC16" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcreapi</b>(3), <b>pcre_config</b>(3). +</P> +<br><a name="SEC17" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC18" href="#TOC1">REVISION</a><br> +<P> +Last updated: 17 March 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrecallout.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrecallout.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrecallout.html Mon Jun 8 18:51:30 2009 @@ -17,6 +17,8 @@ <li><a name="TOC2" href="#SEC2">MISSING CALLOUTS</a> <li><a name="TOC3" href="#SEC3">THE CALLOUT INTERFACE</a> <li><a name="TOC4" href="#SEC4">RETURN VALUES</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE CALLOUTS</a><br> <P> @@ -35,7 +37,7 @@ a number less than 256 after the letter C. The default value is zero. For example, this pattern has two callout points: <pre> - (?C1)\deabc(?C2)def + (?C1)abc(?C2)def </pre> If the PCRE_AUTO_CALLOUT option bit is set when <b>pcre_compile()</b> is called, PCRE automatically inserts callouts, all with number 255, before each item in @@ -60,7 +62,8 @@ <br><a name="SEC2" href="#TOC1">MISSING CALLOUTS</a><br> <P> You should be aware that, because of optimizations in the way PCRE matches -patterns, callouts sometimes do not happen. For example, if the pattern is +patterns by default, callouts sometimes do not happen. For example, if the +pattern is <pre> ab(?C4)cd </pre> @@ -69,6 +72,12 @@ the callout is never reached. However, with "abyd", though the result is still no match, the callout is obeyed. </P> +<P> +You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE +option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. This slows down the +matching process, but does ensure that callouts such as the example above are +obeyed. +</P> <br><a name="SEC3" href="#TOC1">THE CALLOUT INTERFACE</a><br> <P> During matching, when PCRE reaches a callout point, the external function @@ -113,10 +122,12 @@ that were passed to <b>pcre_exec()</b>. </P> <P> -The <i>start_match</i> field contains the offset within the subject at which the -current match attempt started. If the pattern is not anchored, the callout -function may be called several times from the same point in the pattern for -different starting points in the subject. +The <i>start_match</i> field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \K +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. </P> <P> The <i>current_position</i> field contains the offset within the subject of the @@ -177,10 +188,21 @@ The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; it will never be used by PCRE itself. </P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> <P> -Last updated: 28 February 2005 +Last updated: 15 March 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2005 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrecompat.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrecompat.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrecompat.html Mon Jun 8 18:51:30 2009 @@ -17,8 +17,9 @@ </b><br> <P> This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are with respect to Perl -5.8. +regular expressions. The differences described here are mainly with respect to +Perl 5.8, though PCRE versions 7.0 and later contain some features that are +expected to be in the forthcoming Perl 5.10. </P> <P> 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what @@ -76,20 +77,34 @@ The \Q...\E sequence is recognized both inside and outside character classes. </P> <P> -8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) -constructions. However, there is support for recursive patterns using the -non-Perl items (?R), (?number), and (?P>name). Also, the PCRE "callout" feature -allows an external function to be called during pattern matching. See the +8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE "callout" +feature allows an external function to be called during pattern matching. See +the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation for details. </P> <P> -9. There are some differences that are concerned with the settings of captured +9. Subpatterns that are called recursively or as "subroutines" are always +treated as atomic groups in PCRE. This is like Python, but unlike Perl. +</P> +<P> +10. There are some differences that are concerned with the settings of captured strings when part of a pattern is repeated. For example, matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". </P> <P> -10. PCRE provides some extensions to the Perl regular expression facilities: +11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), (*FAIL), (*F), +(*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in the forms without an +argument. PCRE does not support (*MARK). If (*ACCEPT) is within capturing +parentheses, PCRE does not set that capture group; this is different to Perl. +</P> +<P> +12. PCRE provides some extensions to the Perl regular expression facilities. +Perl 5.10 will include new features that are not in earlier versions, some of +which (such as named parentheses) have been in PCRE for some time. This list is +with respect to Perl 5.10: <br> <br> (a) Although lookbehind assertions must match fixed length strings, each @@ -102,8 +117,8 @@ <br> <br> (c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. Otherwise, like Perl, the backslash is ignored. (Perl can -be made to issue a warning.) +meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. +(Perl can be made to issue a warning.) <br> <br> (d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is @@ -119,38 +134,46 @@ options for <b>pcre_exec()</b> have no Perl equivalents. <br> <br> -(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern -matching (Perl can do this using the (?p{code}) construct, which PCRE cannot -support.) +(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. <br> <br> -(h) PCRE supports named capturing substrings, using the Python syntax. +(h) The callout facility is PCRE-specific. <br> <br> -(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java -package. +(i) The partial matching facility is PCRE-specific. <br> <br> -(j) The (R) condition, for testing recursion, is a PCRE extension. -<br> +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. <br> -(k) The callout facility is PCRE-specific. <br> +(k) The alternative matching function (<b>pcre_dfa_exec()</b>) matches in a +different way and is not Perl-compatible. <br> -(l) The partial matching facility is PCRE-specific. <br> +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel <br> -(m) Patterns compiled by PCRE can be saved and re-used at a later time, even on -different hosts that have the other endianness. +University Computing Service <br> +Cambridge CB2 3QH, England. <br> -(n) The alternative matching function (<b>pcre_dfa_exec()</b>) matches in a -different way and is not Perl-compatible. </P> +<br><b> +REVISION +</b><br> <P> -Last updated: 06 June 2006 +Last updated: 11 September 2007 +<br> +Copyright © 1997-2007 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrecpp.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrecpp.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrecpp.html Mon Jun 8 18:51:30 2009 @@ -16,20 +16,20 @@ <li><a name="TOC1" href="#SEC1">SYNOPSIS OF C++ WRAPPER</a> <li><a name="TOC2" href="#SEC2">DESCRIPTION</a> <li><a name="TOC3" href="#SEC3">MATCHING INTERFACE</a> -<li><a name="TOC4" href="#SEC4">PARTIAL MATCHES</a> -<li><a name="TOC5" href="#SEC5">UTF-8 AND THE MATCHING INTERFACE</a> -<li><a name="TOC6" href="#SEC6">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a> -<li><a name="TOC7" href="#SEC7">SCANNING TEXT INCREMENTALLY</a> -<li><a name="TOC8" href="#SEC8">PARSING HEX/OCTAL/C-RADIX NUMBERS</a> -<li><a name="TOC9" href="#SEC9">REPLACING PARTS OF STRINGS</a> -<li><a name="TOC10" href="#SEC10">AUTHOR</a> +<li><a name="TOC4" href="#SEC4">QUOTING METACHARACTERS</a> +<li><a name="TOC5" href="#SEC5">PARTIAL MATCHES</a> +<li><a name="TOC6" href="#SEC6">UTF-8 AND THE MATCHING INTERFACE</a> +<li><a name="TOC7" href="#SEC7">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a> +<li><a name="TOC8" href="#SEC8">SCANNING TEXT INCREMENTALLY</a> +<li><a name="TOC9" href="#SEC9">PARSING HEX/OCTAL/C-RADIX NUMBERS</a> +<li><a name="TOC10" href="#SEC10">REPLACING PARTS OF STRINGS</a> +<li><a name="TOC11" href="#SEC11">AUTHOR</a> +<li><a name="TOC12" href="#SEC12">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">SYNOPSIS OF C++ WRAPPER</a><br> <P> <b>#include <pcrecpp.h></b> </P> -<P> -</P> <br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> <P> The C++ wrapper for PCRE was provided by Google Inc. Some additional @@ -101,16 +101,43 @@ c. The "i"th argument has a suitable type for holding the string captured as the "i"th sub-pattern. If you pass in - NULL for the "i"th argument, or pass fewer arguments than + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the number of sub-patterns, "i"th captured sub-pattern is ignored. </pre> +CAVEAT: An optional sub-pattern that does not exist in the matched +string is assigned the empty string. Therefore, the following will +return false (because the empty string is not a valid number): +<pre> + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); +</pre> The matching interface supports at most 16 arguments per call. If you need more, consider using the more general interface <b>pcrecpp::RE::DoMatch</b>. See <b>pcrecpp.h</b> for the signature for <b>DoMatch</b>. </P> -<br><a name="SEC4" href="#TOC1">PARTIAL MATCHES</a><br> +<P> +NOTE: Do not use <b>no_arg</b>, which is used internally to mark the end of a +list of optional arguments, as a placeholder for missing arguments, as this can +lead to segfaults. +</P> +<br><a name="SEC4" href="#TOC1">QUOTING METACHARACTERS</a><br> +<P> +You can use the "QuoteMeta" operation to insert backslashes before all +potentially meaningful characters in a string. The returned string, used as a +regular expression, will exactly match the original string. +<pre> + Example: + string quoted = RE::QuoteMeta(unquoted); +</pre> +Note that it's legal to escape a character even if it has no special meaning in +a regular expression -- so this function does that. (This also makes it +identical to the perl function of the same name; see "perldoc -f quotemeta".) +For example, "1.5-2.0?" becomes "1\.5\-2\.0\?". +</P> +<br><a name="SEC5" href="#TOC1">PARTIAL MATCHES</a><br> <P> You can use the "PartialMatch" operation when you want the pattern to match any substring of the text. @@ -125,7 +152,7 @@ assert(number == 100); </PRE> </P> -<br><a name="SEC5" href="#TOC1">UTF-8 AND THE MATCHING INTERFACE</a><br> +<br><a name="SEC6" href="#TOC1">UTF-8 AND THE MATCHING INTERFACE</a><br> <P> By default, pattern and text are plain text, one byte per character. The UTF8 flag, passed to the constructor, causes both pattern and string to be treated @@ -150,7 +177,7 @@ --enable-utf8 flag. </PRE> </P> -<br><a name="SEC6" href="#TOC1">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a><br> +<br><a name="SEC7" href="#TOC1">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a><br> <P> PCRE defines some modifiers to change the behavior of the regular expression engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to @@ -244,7 +271,7 @@ </PRE> </P> -<br><a name="SEC7" href="#TOC1">SCANNING TEXT INCREMENTALLY</a><br> +<br><a name="SEC8" href="#TOC1">SCANNING TEXT INCREMENTALLY</a><br> <P> The "Consume" operation may be useful if you want to repeatedly match regular expressions at the front of a string and skip over @@ -277,7 +304,7 @@ pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) </PRE> </P> -<br><a name="SEC8" href="#TOC1">PARSING HEX/OCTAL/C-RADIX NUMBERS</a><br> +<br><a name="SEC9" href="#TOC1">PARSING HEX/OCTAL/C-RADIX NUMBERS</a><br> <P> By default, if you pass a pointer to a numeric value, the corresponding text is interpreted as a base-10 number. You can @@ -295,7 +322,7 @@ </pre> will leave 64 in a, b, c, and d. </P> -<br><a name="SEC9" href="#TOC1">REPLACING PARTS OF STRINGS</a><br> +<br><a name="SEC10" href="#TOC1">REPLACING PARTS OF STRINGS</a><br> <P> You can replace the first match of "pattern" in "str" with "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9) can be @@ -327,11 +354,17 @@ occurred and the extraction happened successfully; if no match occurs, the string is left unaffected. </P> -<br><a name="SEC10" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC11" href="#TOC1">AUTHOR</a><br> <P> The C++ wrapper was contributed by Google Inc. <br> -Copyright © 2005 Google Inc. +Copyright © 2007 Google Inc. +<br> +</P> +<br><a name="SEC12" href="#TOC1">REVISION</a><br> +<P> +Last updated: 17 March 2009 +<br> <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcregrep.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcregrep.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcregrep.html Mon Jun 8 18:51:30 2009 @@ -15,14 +15,17 @@ <ul> <li><a name="TOC1" href="#SEC1">SYNOPSIS</a> <li><a name="TOC2" href="#SEC2">DESCRIPTION</a> -<li><a name="TOC3" href="#SEC3">OPTIONS</a> -<li><a name="TOC4" href="#SEC4">ENVIRONMENT VARIABLES</a> -<li><a name="TOC5" href="#SEC5">NEWLINES</a> -<li><a name="TOC6" href="#SEC6">OPTIONS COMPATIBILITY</a> -<li><a name="TOC7" href="#SEC7">OPTIONS WITH DATA</a> -<li><a name="TOC8" href="#SEC8">MATCHING ERRORS</a> -<li><a name="TOC9" href="#SEC9">DIAGNOSTICS</a> -<li><a name="TOC10" href="#SEC10">AUTHOR</a> +<li><a name="TOC3" href="#SEC3">SUPPORT FOR COMPRESSED FILES</a> +<li><a name="TOC4" href="#SEC4">OPTIONS</a> +<li><a name="TOC5" href="#SEC5">ENVIRONMENT VARIABLES</a> +<li><a name="TOC6" href="#SEC6">NEWLINES</a> +<li><a name="TOC7" href="#SEC7">OPTIONS COMPATIBILITY</a> +<li><a name="TOC8" href="#SEC8">OPTIONS WITH DATA</a> +<li><a name="TOC9" href="#SEC9">MATCHING ERRORS</a> +<li><a name="TOC10" href="#SEC10">DIAGNOSTICS</a> +<li><a name="TOC11" href="#SEC11">SEE ALSO</a> +<li><a name="TOC12" href="#SEC12">AUTHOR</a> +<li><a name="TOC13" href="#SEC13">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> <P> @@ -33,9 +36,9 @@ <b>pcregrep</b> searches files for character patterns, in the same way as other grep commands do, but it uses the PCRE regular expression library to support patterns that are compatible with the regular expressions of Perl 5. See -<a href="pcrepattern.html"><b>pcrepattern</b></a> -for a full description of syntax and semantics of the regular expressions that -PCRE supports. +<a href="pcrepattern.html"><b>pcrepattern</b>(3)</a> +for a full description of syntax and semantics of the regular expressions +that PCRE supports. </P> <P> Patterns, whether supplied on the command line or in a separate file, are given @@ -45,9 +48,9 @@ </pre> If you attempt to use delimiters (for example, by surrounding a pattern with slashes, as is common in Perl scripts), they are interpreted as part of the -pattern. Quotes can of course be used on the command line because they are -interpreted by the shell, and indeed they are required if a pattern contains -white space or shell metacharacters. +pattern. Quotes can of course be used to delimit patterns on the command line +because they are interpreted by the shell, and indeed they are required if a +pattern contains white space or shell metacharacters. </P> <P> The first argument that follows any option settings is treated as the single @@ -63,23 +66,58 @@ <pre> pcregrep some-pattern /file1 - /file3 </pre> -By default, each line that matches the pattern is copied to the standard +By default, each line that matches a pattern is copied to the standard output, and if there is more than one file, the file name is output at the -start of each line. However, there are options that can change how -<b>pcregrep</b> behaves. In particular, the <b>-M</b> option makes it possible to -search for patterns that span line boundaries. What defines a line boundary is -controlled by the <b>-N</b> (<b>--newline</b>) option. +start of each line, followed by a colon. However, there are options that can +change how <b>pcregrep</b> behaves. In particular, the <b>-M</b> option makes it +possible to search for patterns that span line boundaries. What defines a line +boundary is controlled by the <b>-N</b> (<b>--newline</b>) option. </P> <P> Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. -BUFSIZ is defined in <b><stdio.h></b>. +BUFSIZ is defined in <b><stdio.h></b>. When there is more than one pattern +(specified by the use of <b>-e</b> and/or <b>-f</b>), each pattern is applied to +each line in the order in which they are defined, except that all the <b>-e</b> +patterns are tried before the <b>-f</b> patterns. +</P> +<P> +By default, as soon as one pattern matches (or fails to match when <b>-v</b> is +used), no further patterns are considered. However, if <b>--colour</b> (or +<b>--color</b>) is used to colour the matching substrings, or if +<b>--only-matching</b>, <b>--file-offsets</b>, or <b>--line-offsets</b> is used to +output only the part of the line that matched (either shown literally, or as an +offset), scanning resumes immediately following the match, so that further +matches on the same line can be found. If there are multiple patterns, they are +all tried on the remainder of the line, but patterns that follow the one that +matched are not tried on the earlier part of the line. +</P> +<P> +This is the same behaviour as GNU grep, but it does mean that the order in +which multiple patterns are specified can affect the output when one of the +above options is used. +</P> +<P> +Patterns that can match an empty string are accepted, but empty string +matches are not recognized. An example is the pattern "(super)?(man)?", in +which all components are optional. This pattern finds all occurrences of both +"super" and "man"; the output differs from matching with "super|man" when only +the matching substrings are being shown. </P> <P> If the <b>LC_ALL</b> or <b>LC_CTYPE</b> environment variable is set, <b>pcregrep</b> uses the value to set a locale when calling the PCRE library. The <b>--locale</b> option can be used to override this. </P> -<br><a name="SEC3" href="#TOC1">OPTIONS</a><br> +<br><a name="SEC3" href="#TOC1">SUPPORT FOR COMPRESSED FILES</a><br> +<P> +It is possible to compile <b>pcregrep</b> so that it uses <b>libz</b> or +<b>libbz2</b> to read files whose names end in <b>.gz</b> or <b>.bz2</b>, +respectively. You can find out whether your binary has support for one or both +of these file types by running it with the <b>--help</b> option. If the +appropriate support is not present, files are treated as plain text. The +standard input is always so treated. +</P> +<br><a name="SEC4" href="#TOC1">OPTIONS</a><br> <P> <b>--</b> This terminate the list of options. It is useful if the next item on the @@ -124,16 +162,21 @@ </P> <P> <b>--colour=</b><i>value</i>, <b>--color=</b><i>value</i> -This option specifies under what circumstances the part of a line that matched -a pattern should be coloured in the output. The value may be "never" (the -default), "always", or "auto". In the latter case, colouring happens only if -the standard output is connected to a terminal. The colour can be specified by -setting the environment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value -of this variable should be a string of two numbers, separated by a semicolon. -They are copied directly into the control string for setting colour on a -terminal, so it is your responsibility to ensure that they make sense. If -neither of the environment variables is set, the default is "1;31", which gives -red. +This option specifies under what circumstances the parts of a line that matched +a pattern should be coloured in the output. By default, the output is not +coloured. The value (which is optional, see above) may be "never", "always", or +"auto". In the latter case, colouring happens only if the standard output is +connected to a terminal. More resources are used when colouring is enabled, +because <b>pcregrep</b> has to search for all possible matches in a line, not +just one, in order to colour them all. +</P> +<P> +The colour that is used can be specified by setting the environment variable +PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a +string of two numbers, separated by a semicolon. They are copied directly into +the control string for setting colour on a terminal, so it is your +responsibility to ensure that they make sense. If neither of the environment +variables is set, the default is "1;31", which gives red. </P> <P> <b>-D</b> <i>action</i>, <b>--devices=</b><i>action</i> @@ -150,30 +193,43 @@ of reading a directory like this is an immediate end-of-file. </P> <P> -<b>-e</b> <i>pattern</i>, <b>--regex=</b><i>pattern</i>, -<b>--regexp=</b><i>pattern</i> Specify a pattern to be matched. This option can -be used multiple times in order to specify several patterns. It can also be -used as a way of specifying a single pattern that starts with a hyphen. When -<b>-e</b> is used, no argument pattern is taken from the command line; all -arguments are treated as file names. There is an overall maximum of 100 -patterns. They are applied to each line in the order in which they are defined -until one matches (or fails to match if <b>-v</b> is used). If <b>-f</b> is used -with <b>-e</b>, the command line patterns are matched first, followed by the -patterns from the file, independent of the order in which these options are -specified. Note that multiple use of <b>-e</b> is not the same as a single -pattern with alternatives. For example, X|Y finds the first character in a line -that is X or Y, whereas if the two patterns are given separately, -<b>pcregrep</b> finds X if it is present, even if it follows Y in the line. It -finds Y only if there is no X in the line. This really matters only if you are -using <b>-o</b> to show the portion of the line that matched. +<b>-e</b> <i>pattern</i>, <b>--regex=</b><i>pattern</i>, <b>--regexp=</b><i>pattern</i> +Specify a pattern to be matched. This option can be used multiple times in +order to specify several patterns. It can also be used as a way of specifying a +single pattern that starts with a hyphen. When <b>-e</b> is used, no argument +pattern is taken from the command line; all arguments are treated as file +names. There is an overall maximum of 100 patterns. They are applied to each +line in the order in which they are defined until one matches (or fails to +match if <b>-v</b> is used). If <b>-f</b> is used with <b>-e</b>, the command line +patterns are matched first, followed by the patterns from the file, independent +of the order in which these options are specified. Note that multiple use of +<b>-e</b> is not the same as a single pattern with alternatives. For example, +X|Y finds the first character in a line that is X or Y, whereas if the two +patterns are given separately, <b>pcregrep</b> finds X if it is present, even if +it follows Y in the line. It finds Y only if there is no X in the line. This +really matters only if you are using <b>-o</b> to show the part(s) of the line +that matched. </P> <P> <b>--exclude</b>=<i>pattern</i> When <b>pcregrep</b> is searching the files in a directory as a consequence of -the <b>-r</b> (recursive search) option, any files whose names match the pattern -are excluded. The pattern is a PCRE regular expression. If a file name matches -both <b>--include</b> and <b>--exclude</b>, it is excluded. There is no short -form for this option. +the <b>-r</b> (recursive search) option, any regular files whose names match the +pattern are excluded. Subdirectories are not excluded by this option; they are +searched recursively, subject to the <b>--exclude_dir</b> and +<b>--include_dir</b> options. The pattern is a PCRE regular expression, and is +matched against the final component of the file name (not the entire path). If +a file name matches both <b>--include</b> and <b>--exclude</b>, it is excluded. +There is no short form for this option. +</P> +<P> +<b>--exclude_dir</b>=<i>pattern</i> +When <b>pcregrep</b> is searching the contents of a directory as a consequence +of the <b>-r</b> (recursive search) option, any subdirectories whose names match +the pattern are excluded. (Note that the \fP--exclude\fP option does not affect +subdirectories.) The pattern is a PCRE regular expression, and is matched +against the final component of the name (not the entire path). If a +subdirectory name matches both <b>--include_dir</b> and <b>--exclude_dir</b>, it +is excluded. There is no short form for this option. </P> <P> <b>-F</b>, <b>--fixed-strings</b> @@ -193,27 +249,37 @@ is taken from the command line; all arguments are treated as file names. There is an overall maximum of 100 patterns. Trailing white space is removed from each line, and blank lines are ignored. An empty file contains no patterns and -therefore matches nothing. +therefore matches nothing. See also the comments about multiple patterns versus +a single pattern with alternatives in the description of <b>-e</b> above. +</P> +<P> +<b>--file-offsets</b> +Instead of showing lines or parts of lines that match, show each match as an +offset from the start of the file and a length, separated by a comma. In this +mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> +options are ignored. If there is more than one match in a line, each of them is +shown separately. This option is mutually exclusive with <b>--line-offsets</b> +and <b>--only-matching</b>. </P> <P> <b>-H</b>, <b>--with-filename</b> Force the inclusion of the filename at the start of output lines when searching a single file. By default, the filename is not shown in this case. For matching -lines, the filename is followed by a colon and a space; for context lines, a -hyphen separator is used. If a line number is also being output, it follows the -file name without a space. +lines, the filename is followed by a colon; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name. </P> <P> <b>-h</b>, <b>--no-filename</b> Suppress the output filenames when searching multiple files. By default, filenames are shown when multiple files are searched. For matching lines, the -filename is followed by a colon and a space; for context lines, a hyphen -separator is used. If a line number is also being output, it follows the file -name without a space. +filename is followed by a colon; for context lines, a hyphen separator is used. +If a line number is also being output, it follows the file name. </P> <P> <b>--help</b> -Output a brief help message and exit. +Output a help message, giving brief details of the command options and file +type support, and then exit. </P> <P> <b>-i</b>, <b>--ignore-case</b> @@ -222,10 +288,23 @@ <P> <b>--include</b>=<i>pattern</i> When <b>pcregrep</b> is searching the files in a directory as a consequence of -the <b>-r</b> (recursive search) option, only those files whose names match the -pattern are included. The pattern is a PCRE regular expression. If a file name -matches both <b>--include</b> and <b>--exclude</b>, it is excluded. There is no -short form for this option. +the <b>-r</b> (recursive search) option, only those regular files whose names +match the pattern are included. Subdirectories are always included and searched +recursively, subject to the \fP--include_dir\fP and <b>--exclude_dir</b> +options. The pattern is a PCRE regular expression, and is matched against the +final component of the file name (not the entire path). If a file name matches +both <b>--include</b> and <b>--exclude</b>, it is excluded. There is no short +form for this option. +</P> +<P> +<b>--include_dir</b>=<i>pattern</i> +When <b>pcregrep</b> is searching the contents of a directory as a consequence +of the <b>-r</b> (recursive search) option, only those subdirectories whose +names match the pattern are included. (Note that the <b>--include</b> option +does not affect subdirectories.) The pattern is a PCRE regular expression, and +is matched against the final component of the name (not the entire path). If a +subdirectory name matches both <b>--include_dir</b> and <b>--exclude_dir</b>, it +is excluded. There is no short form for this option. </P> <P> <b>-L</b>, <b>--files-without-match</b> @@ -247,6 +326,16 @@ short form for this option. </P> <P> +<b>--line-offsets</b> +Instead of showing lines or parts of lines that match, show each match as a +line number, the offset from the start of the line, and a length. The line +number is terminated by a colon (as usual; see the <b>-n</b> option), and the +offset and length are separated by a comma. In this mode, no context is shown. +That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> options are ignored. If there is +more than one match in a line, each of them is shown separately. This option is +mutually exclusive with <b>--file-offsets</b> and <b>--only-matching</b>. +</P> +<P> <b>--locale</b>=<i>locale-name</i> This option specifies a locale to be used for pattern matching. It overrides the value in the <b>LC_ALL</b> or <b>LC_CTYPE</b> environment variables. If no @@ -268,28 +357,41 @@ </P> <P> <b>-N</b> <i>newline-type</i>, <b>--newline=</b><i>newline-type</i> -The PCRE library supports three different character sequences for indicating +The PCRE library supports five different conventions for indicating the ends of lines. They are the single-character sequences CR (carriage return) -and LF (linefeed), and the two-character sequence CR, LF. When the library is -built, a default line-ending sequence is specified. This is normally the -standard sequence for the operating system. Unless otherwise specified by this -option, <b>pcregrep</b> uses the default. The possible values for this option -are CR, LF, or CRLF. This makes it possible to use <b>pcregrep</b> on files that -have come from other environments without having to modify their line endings. -If the data that is being scanned does not agree with the convention set by -this option, <b>pcregrep</b> may behave in strange ways. +and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, +which recognizes any of the preceding three types, and an "any" convention, in +which any Unicode line ending sequence is assumed to end a line. The Unicode +sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF +(formfeed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and +PS (paragraph separator, U+2029). +<br> +<br> +When the PCRE library is built, a default line-ending sequence is specified. +This is normally the standard sequence for the operating system. Unless +otherwise specified by this option, <b>pcregrep</b> uses the library's default. +The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This +makes it possible to use <b>pcregrep</b> on files that have come from other +environments without having to modify their line endings. If the data that is +being scanned does not agree with the convention set by this option, +<b>pcregrep</b> may behave in strange ways. </P> <P> <b>-n</b>, <b>--line-number</b> Precede each output line by its line number in the file, followed by a colon -and a space for matching lines or a hyphen and a space for context lines. If -the filename is also being output, it precedes the line number. +for matching lines or a hyphen for context lines. If the filename is also being +output, it precedes the line number. This option is forced if +<b>--line-offsets</b> is used. </P> <P> <b>-o</b>, <b>--only-matching</b> Show only the part of the line that matched a pattern. In this mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> options are -ignored. +ignored. If there is more than one match in a line, each of them is shown +separately. If <b>-o</b> is combined with <b>-v</b> (invert the sense of the +match to find non-matching lines), no output is generated, but the return code +is set appropriately. This option is mutually exclusive with +<b>--file-offsets</b> and <b>--line-offsets</b>. </P> <P> <b>-q</b>, <b>--quiet</b> @@ -332,20 +434,20 @@ at the start and end of the pattern. </P> <P> -<b>-x</b>, <b>--line-regex</b>, \fP--line-regexp\fP +<b>-x</b>, <b>--line-regex</b>, <b>--line-regexp</b> Force the patterns to be anchored (each must start matching at the beginning of a line) and in addition, require them to match entire lines. This is equivalent to having ^ and $ characters at the start and end of each alternative branch in every pattern. </P> -<br><a name="SEC4" href="#TOC1">ENVIRONMENT VARIABLES</a><br> +<br><a name="SEC5" href="#TOC1">ENVIRONMENT VARIABLES</a><br> <P> The environment variables <b>LC_ALL</b> and <b>LC_CTYPE</b> are examined, in that order, for a locale. The first one that is set is used. This can be overridden by the <b>--locale</b> option. If no locale is set, the PCRE library's default (usually the "C" locale) is used. </P> -<br><a name="SEC5" href="#TOC1">NEWLINES</a><br> +<br><a name="SEC6" href="#TOC1">NEWLINES</a><br> <P> The <b>-N</b> (<b>--newline</b>) option allows <b>pcregrep</b> to scan files with different newline conventions from the default. However, the setting of this @@ -354,7 +456,7 @@ <b>printf()</b> calls to indicate newlines, relying on the C I/O library to convert this to an appropriate sequence if the output is sent to a file. </P> -<br><a name="SEC6" href="#TOC1">OPTIONS COMPATIBILITY</a><br> +<br><a name="SEC7" href="#TOC1">OPTIONS COMPATIBILITY</a><br> <P> The majority of short and long forms of <b>pcregrep</b>'s options are the same as in the GNU <b>grep</b> program. Any long option of the form @@ -362,7 +464,7 @@ (PCRE terminology). However, the <b>--locale</b>, <b>-M</b>, <b>--multiline</b>, <b>-u</b>, and <b>--utf-8</b> options are specific to <b>pcregrep</b>. </P> -<br><a name="SEC7" href="#TOC1">OPTIONS WITH DATA</a><br> +<br><a name="SEC8" href="#TOC1">OPTIONS WITH DATA</a><br> <P> There are four different ways in which an option with data can be specified. If a short form option is used, the data may follow immediately, or in the next @@ -389,7 +491,7 @@ in the first form, using an equals character. Otherwise it will be assumed that it has no data. </P> -<br><a name="SEC8" href="#TOC1">MATCHING ERRORS</a><br> +<br><a name="SEC9" href="#TOC1">MATCHING ERRORS</a><br> <P> It is possible to supply a regular expression that takes a very long time to fail to match certain lines. Such patterns normally involve nested indefinite @@ -399,7 +501,7 @@ message and the line that caused the problem to the standard error stream. If there are more than 20 such errors, <b>pcregrep</b> gives up. </P> -<br><a name="SEC9" href="#TOC1">DIAGNOSTICS</a><br> +<br><a name="SEC10" href="#TOC1">DIAGNOSTICS</a><br> <P> Exit status is 0 if any matches were found, 1 if no matches were found, and 2 for syntax errors and non-existent or inacessible files (even if matches were @@ -407,18 +509,25 @@ suppress error messages about inaccessble files does not affect the return code. </P> -<br><a name="SEC10" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC11" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcrepattern</b>(3), <b>pcretest</b>(1). +</P> +<br><a name="SEC12" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> University Computing Service <br> -Cambridge CB2 3QG, England. +Cambridge CB2 3QH, England. +<br> </P> +<br><a name="SEC13" href="#TOC1">REVISION</a><br> <P> -Last updated: 06 June 2006 +Last updated: 01 March 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrematching.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrematching.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrematching.html Mon Jun 8 18:51:30 2009 @@ -16,9 +16,11 @@ <li><a name="TOC1" href="#SEC1">PCRE MATCHING ALGORITHMS</a> <li><a name="TOC2" href="#SEC2">REGULAR EXPRESSIONS AS TREES</a> <li><a name="TOC3" href="#SEC3">THE STANDARD MATCHING ALGORITHM</a> -<li><a name="TOC4" href="#SEC4">THE DFA MATCHING ALGORITHM</a> -<li><a name="TOC5" href="#SEC5">ADVANTAGES OF THE DFA ALGORITHM</a> -<li><a name="TOC6" href="#SEC6">DISADVANTAGES OF THE DFA ALGORITHM</a> +<li><a name="TOC4" href="#SEC4">THE ALTERNATIVE MATCHING ALGORITHM</a> +<li><a name="TOC5" href="#SEC5">ADVANTAGES OF THE ALTERNATIVE ALGORITHM</a> +<li><a name="TOC6" href="#SEC6">DISADVANTAGES OF THE ALTERNATIVE ALGORITHM</a> +<li><a name="TOC7" href="#SEC7">AUTHOR</a> +<li><a name="TOC8" href="#SEC8">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE MATCHING ALGORITHMS</a><br> <P> @@ -46,7 +48,7 @@ <something> <something else> <something further> </pre> there are three possible answers. The standard algorithm finds only one of -them, whereas the DFA algorithm finds all three. +them, whereas the alternative algorithm finds all three. </P> <br><a name="SEC2" href="#TOC1">REGULAR EXPRESSIONS AS TREES</a><br> <P> @@ -59,8 +61,8 @@ </P> <br><a name="SEC3" href="#TOC1">THE STANDARD MATCHING ALGORITHM</a><br> <P> -In the terminology of Jeffrey Friedl's book \fIMastering Regular -Expressions\fP, the standard algorithm is an "NFA algorithm". It conducts a +In the terminology of Jeffrey Friedl's book "Mastering Regular +Expressions", the standard algorithm is an "NFA algorithm". It conducts a depth-first search of the pattern tree. That is, it proceeds along a single path through the tree, checking that the subject matches what is required. When there is a mismatch, the algorithm tries any alternatives at the current point, @@ -83,14 +85,15 @@ matched by portions of the pattern in parentheses. This provides support for capturing parentheses and back references. </P> -<br><a name="SEC4" href="#TOC1">THE DFA MATCHING ALGORITHM</a><br> +<br><a name="SEC4" href="#TOC1">THE ALTERNATIVE MATCHING ALGORITHM</a><br> <P> -DFA stands for "deterministic finite automaton", but you do not need to -understand the origins of that name. This algorithm conducts a breadth-first -search of the tree. Starting from the first matching point in the subject, it -scans the subject string from left to right, once, character by character, and -as it does this, it remembers all the paths through the tree that represent -valid matches. +This algorithm conducts a breadth-first search of the tree. Starting from the +first matching point in the subject, it scans the subject string from left to +right, once, character by character, and as it does this, it remembers all the +paths through the tree that represent valid matches. In Friedl's terminology, +this is a kind of "DFA algorithm", though it is not implemented as a +traditional finite state machine (it keeps multiple states active +simultaneously). </P> <P> The scan continues until either the end of the subject is reached, or there are @@ -114,12 +117,21 @@ </P> <P> There are a number of features of PCRE regular expressions that are not -supported by the DFA matching algorithm. They are as follows: +supported by the alternative matching algorithm. They are as follows: </P> <P> 1. Because the algorithm finds all possible matches, the greedy or ungreedy nature of repetition quantifiers is not relevant. Greedy and ungreedy -quantifiers are treated in exactly the same way. +quantifiers are treated in exactly the same way. However, possessive +quantifiers can make a difference when what follows could also match what is +quantified, for example in a pattern like this: +<pre> + ^a++\w! +</pre> +This pattern matches "aaab!" but not "aaa!", which would be matched by a +non-possessive quantifier. Similarly, if an atomic group is present, it is +matched as if it were a standalone pattern at the current point, and the +longest match is then "locked in" for the rest of the overall pattern. </P> <P> 2. When dealing with multiple paths through the tree simultaneously, it is not @@ -133,22 +145,30 @@ </P> <P> 4. For the same reason, conditional expressions that use a backreference as the -condition are not supported. +condition or test for a specific group recursion are not supported. +</P> +<P> +5. Because many paths through the tree may be active, the \K escape sequence, +which resets the start of the match when encountered (but may be on some paths +and not on others), is not supported. It causes an error if encountered. </P> <P> -5. Callouts are supported, but the value of the <i>capture_top</i> field is +6. Callouts are supported, but the value of the <i>capture_top</i> field is always 1, and the value of the <i>capture_last</i> field is always -1. </P> <P> -6. -The \C escape sequence, which (in the standard algorithm) matches a single -byte, even in UTF-8 mode, is not supported because the DFA algorithm moves -through the subject string one character at a time, for all active paths +7. The \C escape sequence, which (in the standard algorithm) matches a single +byte, even in UTF-8 mode, is not supported because the alternative algorithm +moves through the subject string one character at a time, for all active paths through the tree. </P> -<br><a name="SEC5" href="#TOC1">ADVANTAGES OF THE DFA ALGORITHM</a><br> <P> -Using the DFA matching algorithm provides the following advantages: +8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not +supported. (*FAIL) is supported, and behaves like a failing negative assertion. +</P> +<br><a name="SEC5" href="#TOC1">ADVANTAGES OF THE ALTERNATIVE ALGORITHM</a><br> +<P> +Using the alternative matching algorithm provides the following advantages: </P> <P> 1. All possible matches (at a single point in the subject) are automatically @@ -159,17 +179,18 @@ <P> 2. There is much better support for partial matching. The restrictions on the content of the pattern that apply when using the standard algorithm for partial -matching do not apply to the DFA algorithm. For non-anchored patterns, the -starting position of a partial match is available. +matching do not apply to the alternative algorithm. For non-anchored patterns, +the starting position of a partial match is available. </P> <P> -3. Because the DFA algorithm scans the subject string just once, and never -needs to backtrack, it is possible to pass very long subject strings to the -matching function in several pieces, checking for partial matching each time. +3. Because the alternative algorithm scans the subject string just once, and +never needs to backtrack, it is possible to pass very long subject strings to +the matching function in several pieces, checking for partial matching each +time. </P> -<br><a name="SEC6" href="#TOC1">DISADVANTAGES OF THE DFA ALGORITHM</a><br> +<br><a name="SEC6" href="#TOC1">DISADVANTAGES OF THE ALTERNATIVE ALGORITHM</a><br> <P> -The DFA algorithm suffers from a number of disadvantages: +The alternative algorithm suffers from a number of disadvantages: </P> <P> 1. It is substantially slower than the standard algorithm. This is partly @@ -180,13 +201,24 @@ 2. Capturing parentheses and back references are not supported. </P> <P> -3. The "atomic group" feature of PCRE regular expressions is supported, but -does not provide the advantage that it does for the standard algorithm. +3. Although atomic groups are supported, their use does not provide the +performance advantage that it does for the standard algorithm. </P> +<br><a name="SEC7" href="#TOC1">AUTHOR</a><br> <P> -Last updated: 06 June 2006 +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC8" href="#TOC1">REVISION</a><br> +<P> +Last updated: 19 April 2008 +<br> +Copyright © 1997-2008 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrepartial.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrepartial.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrepartial.html Mon Jun 8 18:51:30 2009 @@ -17,6 +17,8 @@ <li><a name="TOC2" href="#SEC2">RESTRICTED PATTERNS FOR PCRE_PARTIAL</a> <li><a name="TOC3" href="#SEC3">EXAMPLE OF PARTIAL MATCHING USING PCRETEST</a> <li><a name="TOC4" href="#SEC4">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec()</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PARTIAL MATCHING IN PCRE</a><br> <P> @@ -90,6 +92,8 @@ <P> If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, <b>pcre_exec()</b> returns the error code PCRE_ERROR_BADPARTIAL (-13). +You can use the PCRE_INFO_OKPARTIAL call to <b>pcre_fullinfo()</b> to find out +if a compiled pattern can be used for partial matching. </P> <br><a name="SEC3" href="#TOC1">EXAMPLE OF PARTIAL MATCHING USING PCRETEST</a><br> <P> @@ -112,8 +116,9 @@ </pre> The first data string is matched completely, so <b>pcretest</b> shows the matched substrings. The remaining four strings do not match the complete -pattern, but the first two are partial matches. The same test, using DFA -matching (by means of the \D escape sequence), produces the following output: +pattern, but the first two are partial matches. The same test, using +<b>pcre_dfa_exec()</b> matching (by means of the \D escape sequence), produces +the following output: <pre> re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 25jun04\P\D @@ -134,11 +139,11 @@ <P> When a partial match has been found using <b>pcre_dfa_exec()</b>, it is possible to continue the match by providing additional subject data and calling -<b>pcre_dfa_exec()</b> again with the PCRE_DFA_RESTART option and the same -working space (where details of the previous partial match are stored). Here is -an example using <b>pcretest</b>, where the \R escape sequence sets the -PCRE_DFA_RESTART option and the \D escape sequence requests the use of -<b>pcre_dfa_exec()</b>: +<b>pcre_dfa_exec()</b> again with the same compiled regular expression, this +time setting the PCRE_DFA_RESTART option. You must also pass the same working +space as before, because this is where details of the previous partial match +are stored. Here is an example using <b>pcretest</b>, using the \R escape +sequence to set the PCRE_DFA_RESTART option (\P and \D are as above): <pre> re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 23ja\P\D @@ -153,9 +158,10 @@ program to do that if it needs to. </P> <P> -This facility can be used to pass very long subject strings to -<b>pcre_dfa_exec()</b>. However, some care is needed for certain types of -pattern. +You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial matching +over multiple segments. This facility can be used to pass very long subject +strings to <b>pcre_dfa_exec()</b>. However, some care is needed for certain +types of pattern. </P> <P> 1. If the pattern contains tests for the beginning or end of a line, you need @@ -165,7 +171,7 @@ <P> 2. If the pattern contains backward assertions (including \b or \B), you need to arrange for some overlap in the subject strings to allow for this. For -example, you could pass the subject in chunks that were 500 bytes long, but in +example, you could pass the subject in chunks that are 500 bytes long, but in a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 bytes at the start of the buffer. </P> @@ -174,7 +180,7 @@ always produce exactly the same result as matching over one single long string. The difference arises when there are multiple matching possibilities, because a partial match result is given only when there are no completed matches in a -call to fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has +call to <b>pcre_dfa_exec()</b>. This means that as soon as the shortest match has been found, continuation to a new subject segment is no longer possible. Consider this <b>pcretest</b> example: <pre> @@ -216,10 +222,21 @@ </pre> where no string can be a partial match for both alternatives. </P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> <P> -Last updated: 16 January 2006 +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<P> +Last updated: 04 June 2007 +<br> +Copyright © 1997-2007 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrepattern.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrepattern.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrepattern.html Mon Jun 8 18:51:30 2009 @@ -14,41 +14,64 @@ <br> <ul> <li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION DETAILS</a> -<li><a name="TOC2" href="#SEC2">BACKSLASH</a> -<li><a name="TOC3" href="#SEC3">CIRCUMFLEX AND DOLLAR</a> -<li><a name="TOC4" href="#SEC4">FULL STOP (PERIOD, DOT)</a> -<li><a name="TOC5" href="#SEC5">MATCHING A SINGLE BYTE</a> -<li><a name="TOC6" href="#SEC6">SQUARE BRACKETS AND CHARACTER CLASSES</a> -<li><a name="TOC7" href="#SEC7">POSIX CHARACTER CLASSES</a> -<li><a name="TOC8" href="#SEC8">VERTICAL BAR</a> -<li><a name="TOC9" href="#SEC9">INTERNAL OPTION SETTING</a> -<li><a name="TOC10" href="#SEC10">SUBPATTERNS</a> -<li><a name="TOC11" href="#SEC11">NAMED SUBPATTERNS</a> -<li><a name="TOC12" href="#SEC12">REPETITION</a> -<li><a name="TOC13" href="#SEC13">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> -<li><a name="TOC14" href="#SEC14">BACK REFERENCES</a> -<li><a name="TOC15" href="#SEC15">ASSERTIONS</a> -<li><a name="TOC16" href="#SEC16">CONDITIONAL SUBPATTERNS</a> -<li><a name="TOC17" href="#SEC17">COMMENTS</a> -<li><a name="TOC18" href="#SEC18">RECURSIVE PATTERNS</a> -<li><a name="TOC19" href="#SEC19">SUBPATTERNS AS SUBROUTINES</a> -<li><a name="TOC20" href="#SEC20">CALLOUTS</a> +<li><a name="TOC2" href="#SEC2">NEWLINE CONVENTIONS</a> +<li><a name="TOC3" href="#SEC3">CHARACTERS AND METACHARACTERS</a> +<li><a name="TOC4" href="#SEC4">BACKSLASH</a> +<li><a name="TOC5" href="#SEC5">CIRCUMFLEX AND DOLLAR</a> +<li><a name="TOC6" href="#SEC6">FULL STOP (PERIOD, DOT)</a> +<li><a name="TOC7" href="#SEC7">MATCHING A SINGLE BYTE</a> +<li><a name="TOC8" href="#SEC8">SQUARE BRACKETS AND CHARACTER CLASSES</a> +<li><a name="TOC9" href="#SEC9">POSIX CHARACTER CLASSES</a> +<li><a name="TOC10" href="#SEC10">VERTICAL BAR</a> +<li><a name="TOC11" href="#SEC11">INTERNAL OPTION SETTING</a> +<li><a name="TOC12" href="#SEC12">SUBPATTERNS</a> +<li><a name="TOC13" href="#SEC13">DUPLICATE SUBPATTERN NUMBERS</a> +<li><a name="TOC14" href="#SEC14">NAMED SUBPATTERNS</a> +<li><a name="TOC15" href="#SEC15">REPETITION</a> +<li><a name="TOC16" href="#SEC16">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> +<li><a name="TOC17" href="#SEC17">BACK REFERENCES</a> +<li><a name="TOC18" href="#SEC18">ASSERTIONS</a> +<li><a name="TOC19" href="#SEC19">CONDITIONAL SUBPATTERNS</a> +<li><a name="TOC20" href="#SEC20">COMMENTS</a> +<li><a name="TOC21" href="#SEC21">RECURSIVE PATTERNS</a> +<li><a name="TOC22" href="#SEC22">SUBPATTERNS AS SUBROUTINES</a> +<li><a name="TOC23" href="#SEC23">ONIGURUMA SUBROUTINE SYNTAX</a> +<li><a name="TOC24" href="#SEC24">CALLOUTS</a> +<li><a name="TOC25" href="#SEC25">BACKTRACKING CONTROL</a> +<li><a name="TOC26" href="#SEC26">SEE ALSO</a> +<li><a name="TOC27" href="#SEC27">AUTHOR</a> +<li><a name="TOC28" href="#SEC28">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION DETAILS</a><br> <P> -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of books, some of which have copious examples. -Jeffrey Friedl's "Mastering Regular Expressions", published by O'Reilly, covers -regular expressions in great detail. This description of PCRE's regular -expressions is intended as reference material. +The syntax and semantics of the regular expressions that are supported by PCRE +are described in detail below. There is a quick-reference syntax summary in the +<a href="pcresyntax.html"><b>pcresyntax</b></a> +page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE +also supports some alternative regular expression syntax (which does not +conflict with the Perl syntax) in order to provide some compatibility with +regular expressions in Python, .NET, and Oniguruma. +</P> +<P> +Perl's regular expressions are described in its own documentation, and +regular expressions in general are covered in a number of books, some of which +have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", +published by O'Reilly, covers regular expressions in great detail. This +description of PCRE's regular expressions is intended as reference material. </P> <P> The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 character strings. To use this, you must build PCRE to include UTF-8 support, and then call <b>pcre_compile()</b> with -the PCRE_UTF8 option. How this affects pattern matching is mentioned in several -places below. There is also a summary of UTF-8 features in the +the PCRE_UTF8 option. There is also a special sequence that can be given at the +start of a pattern: +<pre> + (*UTF8) +</pre> +Starting a pattern with this sequence is equivalent to setting the PCRE_UTF8 +option. This feature is not Perl-compatible. How setting UTF-8 mode affects +pattern matching is mentioned in several places below. There is also a summary +of UTF-8 features in the <a href="pcre.html#utf8support">section on UTF-8 support</a> in the main <a href="pcre.html"><b>pcre</b></a> @@ -59,11 +82,55 @@ PCRE when its main matching function, <b>pcre_exec()</b>, is used. From release 6.0, PCRE offers a second matching function, <b>pcre_dfa_exec()</b>, which matches using a different algorithm that is not -Perl-compatible. The advantages and disadvantages of the alternative function, -and how it differs from the normal function, are discussed in the +Perl-compatible. Some of the features discussed below are not available when +<b>pcre_dfa_exec()</b> is used. The advantages and disadvantages of the +alternative function, and how it differs from the normal function, are +discussed in the <a href="pcrematching.html"><b>pcrematching</b></a> page. </P> +<br><a name="SEC2" href="#TOC1">NEWLINE CONVENTIONS</a><br> +<P> +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The +<a href="pcreapi.html"><b>pcreapi</b></a> +page has +<a href="pcreapi.html#newlines">further discussion</a> +about newlines, and shows how to set the newline convention in the +<i>options</i> arguments for the compiling and matching functions. +</P> +<P> +It is also possible to specify a newline convention by starting a pattern +string with one of the following five sequences: +<pre> + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences +</pre> +These override the default and the options given to <b>pcre_compile()</b>. For +example, on a Unix system where LF is the default newline sequence, the pattern +<pre> + (*CR)a.b +</pre> +changes the convention to CR. That pattern matches "a\nb" because LF is no +longer a newline. Note that these special settings, which are not +Perl-compatible, are recognized only at the very start of a pattern, and that +they must be in upper case. If more than one of them is present, the last one +is used. +</P> +<P> +The newline convention does not affect what the \R escape sequence matches. By +default, this is any Unicode newline sequence, for Perl compatibility. However, +this can be changed; see the description of \R in the section entitled +<a href="#newlineseq">"Newline sequences"</a> +below. A change of \R setting can be combined with a change of newline +convention. +</P> +<br><a name="SEC3" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br> <P> A regular expression is a pattern that is matched against a subject string from left to right. Most characters stand for themselves in a pattern, and match the @@ -90,8 +157,8 @@ <P> There are two different sets of metacharacters: those that are recognized anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the metacharacters are -as follows: +recognized within square brackets. Outside square brackets, the metacharacters +are as follows: <pre> \ general escape character with several uses ^ assert start of string (or line, in multiline mode) @@ -120,7 +187,7 @@ </pre> The following sections describe the use of each of the metacharacters. </P> -<br><a name="SEC2" href="#TOC1">BACKSLASH</a><br> +<br><a name="SEC4" href="#TOC1">BACKSLASH</a><br> <P> The backslash character has several uses. Firstly, if it is followed by a non-alphanumeric character, it takes away any special meaning that character @@ -169,7 +236,7 @@ \cx "control-x", where x is any character \e escape (hex 1B) \f formfeed (hex 0C) - \n newline (hex 0A) + \n linefeed (hex 0A) \r carriage return (hex 0D) \t tab (hex 09) \ddd character with octal code ddd, or backreference @@ -185,11 +252,15 @@ After \x, from zero to two hexadecimal digits are read (letters can be in upper or lower case). Any number of hexadecimal digits may appear between \x{ and }, but the value of the character code must be less than 256 in non-UTF-8 -mode, and less than 2**31 in UTF-8 mode (that is, the maximum hexadecimal value -is 7FFFFFFF). If characters other than hexadecimal digits appear between \x{ -and }, or if there is no terminating }, this form of escape is not recognized. -Instead, the initial \x will be interpreted as a basic hexadecimal escape, -with no following digits, giving a character whose value is zero. +mode, and less than 2**31 in UTF-8 mode. That is, the maximum value in +hexadecimal is 7FFFFFFF. Note that this is bigger than the largest Unicode code +point, which is 10FFFF. +</P> +<P> +If characters other than hexadecimal digits appear between \x{ and }, or if +there is no terminating }, this form of escape is not recognized. Instead, the +initial \x will be interpreted as a basic hexadecimal escape, with no +following digits, giving a character whose value is zero. </P> <P> Characters whose value is less than 256 can be defined by either of the two @@ -216,7 +287,7 @@ <P> Inside a character class, or if the decimal number is greater than 9 and there have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, ane uses them to generate a data character. Any +digits following the backslash, and uses them to generate a data character. Any subsequent digits stand for themselves. In non-UTF-8 mode, the value of a character specified in octal must be less than \400. In UTF-8 mode, values up to \777 are permitted. For example: @@ -238,21 +309,48 @@ All the sequences that define a single character value can be used both inside and outside character classes. In addition, inside a character class, the sequence \b is interpreted as the backspace character (hex 08), and the -sequence \X is interpreted as the character "X". Outside a character class, -these sequences have different meanings +sequences \R and \X are interpreted as the characters "R" and "X", +respectively. Outside a character class, these sequences have different +meanings <a href="#uniextseq">(see below).</a> </P> <br><b> +Absolute and relative back references +</b><br> +<P> +The sequence \g followed by an unsigned or a negative number, optionally +enclosed in braces, is an absolute or relative back reference. A named back +reference can be coded as \g{name}. Back references are discussed +<a href="#backreferences">later,</a> +following the discussion of +<a href="#subpattern">parenthesized subpatterns.</a> +</P> +<br><b> +Absolute and relative subroutine calls +</b><br> +<P> +For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a "subroutine". Details are discussed +<a href="#onigurumasubroutines">later.</a> +Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i> +synonymous. The former is a back reference; the latter is a subroutine call. +</P> +<br><b> Generic character types </b><br> <P> -The third use of backslash is for specifying generic character types. The +Another use of backslash is for specifying generic character types. The following are always recognized: <pre> \d any decimal digit \D any character that is not a decimal digit + \h any horizontal whitespace character + \H any character that is not a horizontal whitespace character \s any whitespace character \S any character that is not a whitespace character + \v any vertical whitespace character + \V any character that is not a vertical whitespace character \w any "word" character \W any "non-word" character </pre> @@ -268,9 +366,53 @@ <P> For compatibility with Perl, \s does not match the VT character (code 11). This makes it different from the the POSIX "space" class. The \s characters -are HT (9), LF (10), FF (12), CR (13), and space (32). (If "use locale;" is +are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is included in a Perl script, \s may match the VT character. In PCRE, it never -does.) +does. +</P> +<P> +In UTF-8 mode, characters with values greater than 128 never match \d, \s, or +\w, and always match \D, \S, and \W. This is true even when Unicode +character property support is available. These sequences retain their original +meanings from before UTF-8 support was available, mainly for efficiency +reasons. Note that this also affects \b, because it is defined in terms of \w +and \W. +</P> +<P> +The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to the +other sequences, these do match certain high-valued codepoints in UTF-8 mode. +The horizontal space characters are: +<pre> + U+0009 Horizontal tab + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space +</pre> +The vertical space characters are: +<pre> + U+000A Linefeed + U+000B Vertical tab + U+000C Formfeed + U+000D Carriage return + U+0085 Next line + U+2028 Line separator + U+2029 Paragraph separator +</PRE> </P> <P> A "word" character is an underscore or any character less than 256 that is a @@ -280,22 +422,67 @@ <a href="pcreapi.html#localesupport">"Locale support"</a> in the <a href="pcreapi.html"><b>pcreapi</b></a> -page). For example, in the "fr_FR" (French) locale, some character codes -greater than 128 are used for accented letters, and these are matched by \w. -</P> +page). For example, in a French locale such as "fr_FR" in Unix-like systems, +or "french" in Windows, some character codes greater than 128 are used for +accented letters, and these are matched by \w. The use of locales with Unicode +is discouraged. +<a name="newlineseq"></a></P> +<br><b> +Newline sequences +</b><br> <P> -In UTF-8 mode, characters with values greater than 128 never match \d, \s, or -\w, and always match \D, \S, and \W. This is true even when Unicode -character property support is available. The use of locales with Unicode is -discouraged. +Outside a character class, by default, the escape sequence \R matches any +Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is +equivalent to the following: +<pre> + (?>\r\n|\n|\x0b|\f|\r|\x85) +</pre> +This is an example of an "atomic group", details of which are given +<a href="#atomicgroup">below.</a> +This particular group matches either the two-character sequence CR followed by +LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, +U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next +line, U+0085). The two-character sequence is treated as a single unit that +cannot be split. +</P> +<P> +In UTF-8 mode, two additional characters whose codepoints are greater than 255 +are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). +Unicode character property support is not needed for these characters to be +recognized. +</P> +<P> +It is possible to restrict \R to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. (BSR is an abbrevation +for "backslash R".) This can be made the default when PCRE is built; if this is +the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. +It is also possible to specify these settings by starting a pattern string with +one of the following sequences: +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +</pre> +These override the default and the options given to <b>pcre_compile()</b>, but +they can be overridden by options given to <b>pcre_exec()</b>. Note that these +special settings, which are not Perl-compatible, are recognized only at the +very start of a pattern, and that they must be in upper case. If more than one +of them is present, the last one is used. They can be combined with a change of +newline convention, for example, a pattern can start with: +<pre> + (*ANY)(*BSR_ANYCRLF) +</pre> +Inside a character class, \R matches the letter "R". <a name="uniextseq"></a></P> <br><b> Unicode character properties </b><br> <P> When PCRE is built with Unicode character property support, three additional -escape sequences to match character properties are available when UTF-8 mode -is selected. They are: +escape sequences that match characters with specific properties are available. +When not in UTF-8 mode, these sequences are of course limited to testing +characters whose codepoints are less than 256, but they do work in this mode. +The extra escape sequences are: <pre> \p{<i>xx</i>} a character with the <i>xx</i> property \P{<i>xx</i>} a character without the <i>xx</i> property @@ -321,6 +508,7 @@ <P> Arabic, Armenian, +Balinese, Bengali, Bopomofo, Braille, @@ -330,6 +518,7 @@ Cherokee, Common, Coptic, +Cuneiform, Cypriot, Cyrillic, Deseret, @@ -359,11 +548,14 @@ Mongolian, Myanmar, New_Tai_Lue, +Nko, Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, +Phags_Pa, +Phoenician, Runic, Shavian, Sinhala, @@ -447,6 +639,14 @@ a modifier or "other". </P> <P> +The Cs (Surrogate) property applies only to characters in the range U+D800 to +U+DFFF. Such characters are not valid in UTF-8 strings (see RFC 3629) and so +cannot be tested by PCRE, unless UTF-8 validity checking has been turned off +(see the discussion of PCRE_NO_UTF8_CHECK in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page). +</P> +<P> The long synonyms for these properties that Perl supports (such as \p{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". @@ -471,19 +671,43 @@ atomic group <a href="#atomicgroup">(see below).</a> Characters with the "mark" property are typically accents that affect the -preceding character. +preceding character. None of them have codepoints less than 256, so in +non-UTF-8 mode \X matches any one character. </P> <P> Matching characters by Unicode property is not fast, because PCRE has to search a structure that contains data for over fifteen thousand characters. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE. +<a name="resetmatchstart"></a></P> +<br><b> +Resetting the match start +</b><br> +<P> +The escape sequence \K, which is a Perl 5.10 feature, causes any previously +matched characters not to be included in the final matched sequence. For +example, the pattern: +<pre> + foo\Kbar +</pre> +matches "foobar", but reports that it has matched "bar". This feature is +similar to a lookbehind assertion +<a href="#lookbehind">(described below).</a> +However, in this case, the part of the subject before the real match does not +have to be of fixed length, as lookbehind assertions do. The use of \K does +not interfere with the setting of +<a href="#subpattern">captured substrings.</a> +For example, when the pattern +<pre> + (foo)\Kbar +</pre> +matches "foobar", the first substring is still set to "foo". <a name="smallassertions"></a></P> <br><b> Simple assertions </b><br> <P> -The fourth use of backslash is for certain simple assertions. An assertion +The final use of backslash is for certain simple assertions. An assertion specifies a condition that has to be met at a particular point in a match, without consuming any characters from the subject string. The use of subpatterns for more complicated assertions is described @@ -492,10 +716,11 @@ <pre> \b matches at a word boundary \B matches when not at a word boundary - \A matches at start of subject - \Z matches at end of subject or before newline at end - \z matches at end of subject - \G matches at first matching position in subject + \A matches at the start of the subject + \Z matches at the end of the subject + also matches before a newline at the end of the subject + \z matches only at the end of the subject + \G matches at the first matching position in the subject </pre> These assertions may not appear in character classes (but note that \b has a different meaning, namely the backspace character, inside a character class). @@ -538,7 +763,7 @@ to the starting match position, and the "anchored" flag is set in the compiled regular expression. </P> -<br><a name="SEC3" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> +<br><a name="SEC5" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> <P> Outside a character class, in the default matching mode, the circumflex character is an assertion that is true only if the current matching point is @@ -592,34 +817,39 @@ end of the subject in both modes, and if all branches of a pattern start with \A it is always anchored, whether or not PCRE_MULTILINE is set. </P> -<br><a name="SEC4" href="#TOC1">FULL STOP (PERIOD, DOT)</a><br> +<br><a name="SEC6" href="#TOC1">FULL STOP (PERIOD, DOT)</a><br> <P> Outside a character class, a dot in the pattern matches any one character in the subject string except (by default) a character that signifies the end of a -line. In UTF-8 mode, the matched character may be more than one byte long. When -a line ending is defined as a single character (CR or LF), dot never matches -that character; when the two-character sequence CRLF is used, dot does not -match CR if it is immediately followed by LF, but otherwise it matches all -characters (including isolated CRs and LFs). +line. In UTF-8 mode, the matched character may be more than one byte long. +</P> +<P> +When a line ending is defined as a single character, dot never matches that +character; when the two-character sequence CRLF is used, dot does not match CR +if it is immediately followed by LF, but otherwise it matches all characters +(including isolated CRs and LFs). When any Unicode line endings are being +recognized, dot does not match CR or LF or any of the other line ending +characters. </P> <P> The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL -option is set, a dot matches any one character, without exception. If newline -is defined as the two-character sequence CRLF, it takes two dots to match it. +option is set, a dot matches any one character, without exception. If the +two-character sequence CRLF is present in the subject string, it takes two dots +to match it. </P> <P> The handling of dot is entirely independent of the handling of circumflex and dollar, the only relationship being that they both involve newlines. Dot has no special meaning in a character class. </P> -<br><a name="SEC5" href="#TOC1">MATCHING A SINGLE BYTE</a><br> +<br><a name="SEC7" href="#TOC1">MATCHING A SINGLE BYTE</a><br> <P> Outside a character class, the escape sequence \C matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches CR and LF. The -feature is provided in Perl in order to match individual bytes in UTF-8 mode. -Because it breaks up UTF-8 characters into individual bytes, what remains in -the string may be a malformed UTF-8 string. For this reason, the \C escape -sequence is best avoided. +in and out of UTF-8 mode. Unlike a dot, it always matches any line-ending +characters. The feature is provided in Perl in order to match individual bytes +in UTF-8 mode. Because it breaks up UTF-8 characters into individual bytes, +what remains in the string may be a malformed UTF-8 string. For this reason, +the \C escape sequence is best avoided. </P> <P> PCRE does not allow \C to appear in lookbehind assertions @@ -627,7 +857,7 @@ because in UTF-8 mode this would make it impossible to calculate the length of the lookbehind. <a name="characterclass"></a></P> -<br><a name="SEC6" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br> +<br><a name="SEC8" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br> <P> An opening square bracket introduces a character class, terminated by a closing square bracket. A closing square bracket on its own is not special. If a @@ -670,10 +900,10 @@ UTF-8 support. </P> <P> -Characters that might indicate line breaks (CR and LF) are never treated in any -special way when matching character classes, whatever line-ending sequence is -in use, and whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is -used. A class such as [^a] always matches one of these characters. +Characters that might indicate line breaks are never treated in any special way +when matching character classes, whatever line-ending sequence is in use, and +whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class +such as [^a] always matches one of these characters. </P> <P> The minus (hyphen) character can be used to specify a range of characters in a @@ -701,7 +931,7 @@ If a range that includes letters is used when caseless matching is set, it matches the letters in either case. For example, [W-c] is equivalent to [][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character -tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches accented E +tables for a French locale are in use, [\xc8-\xcb] matches accented E characters in both cases. In UTF-8 mode, PCRE supports the concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. @@ -722,7 +952,7 @@ closing square bracket. However, escaping other non-alphanumeric characters does no harm. </P> -<br><a name="SEC7" href="#TOC1">POSIX CHARACTER CLASSES</a><br> +<br><a name="SEC9" href="#TOC1">POSIX CHARACTER CLASSES</a><br> <P> Perl supports the POSIX notation for character classes. This uses names enclosed by [: and :] within the enclosing square brackets. PCRE also supports @@ -768,7 +998,7 @@ In UTF-8 mode, characters with values greater than 128 do not match any of the POSIX character classes. </P> -<br><a name="SEC8" href="#TOC1">VERTICAL BAR</a><br> +<br><a name="SEC10" href="#TOC1">VERTICAL BAR</a><br> <P> Vertical bar characters are used to separate alternative patterns. For example, the pattern @@ -783,11 +1013,12 @@ "succeeds" means matching the rest of the main pattern as well as the alternative in the subpattern. </P> -<br><a name="SEC9" href="#TOC1">INTERNAL OPTION SETTING</a><br> +<br><a name="SEC11" href="#TOC1">INTERNAL OPTION SETTING</a><br> <P> The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options can be changed from within the pattern by a sequence of -Perl option letters enclosed between "(?" and ")". The option letters are +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are <pre> i for PCRE_CASELESS m for PCRE_MULTILINE @@ -802,15 +1033,20 @@ unset. </P> <P> -When an option change occurs at top level (that is, not inside subpattern -parentheses), the change applies to the remainder of the pattern that follows. -If the change is placed right at the start of a pattern, PCRE extracts it into -the global options (and it will therefore show up in data extracted by the -<b>pcre_fullinfo()</b> function). +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. </P> <P> -An option change within a subpattern affects only that part of the current -pattern that follows it, so +When one of these option changes occurs at top level (that is, not inside +subpattern parentheses), the change applies to the remainder of the pattern +that follows. If the change is placed right at the start of a pattern, PCRE +extracts it into the global options (and it will therefore show up in data +extracted by the <b>pcre_fullinfo()</b> function). +</P> +<P> +An option change within a subpattern (see below for a description of +subpatterns) affects only that part of the current pattern that follows it, so <pre> (a(?i)b)c </pre> @@ -827,11 +1063,16 @@ behaviour otherwise. </P> <P> -The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be -changed in the same way as the Perl-compatible options by using the characters -J, U and X respectively. +<b>Note:</b> There are other PCRE-specific options that can be set by the +application when the compile or match functions are called. In some cases the +pattern can contain special leading sequences such as (*CRLF) to override what +the application has set or what has been defaulted. Details are given in the +section entitled +<a href="#newlineseq">"Newline sequences"</a> +above. There is also the (*UTF8) leading sequence that can be used to set UTF-8 +mode; this is equivalent to setting the PCRE_UTF8 option. <a name="subpattern"></a></P> -<br><a name="SEC10" href="#TOC1">SUBPATTERNS</a><br> +<br><a name="SEC12" href="#TOC1">SUBPATTERNS</a><br> <P> Subpatterns are delimited by parentheses (round brackets), which can be nested. Turning part of a pattern into a subpattern does two things: @@ -842,7 +1083,7 @@ cat(aract|erpillar|) </pre> matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. +parentheses, it would match "cataract", "erpillar" or an empty string. <br> <br> 2. It sets up the subpattern as a capturing subpattern. This means that, when @@ -870,8 +1111,7 @@ the ((?:red|white) (king|queen)) </pre> the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535, and the maximum depth -of nesting of all subpatterns, both capturing and non-capturing, is 200. +2. The maximum number of capturing subpatterns is 65535. </P> <P> As a convenient shorthand, if any option settings are required at the start of @@ -886,13 +1126,50 @@ is reached, an option setting in one branch does affect subsequent branches, so the above patterns match "SUNDAY" as well as "Saturday". </P> -<br><a name="SEC11" href="#TOC1">NAMED SUBPATTERNS</a><br> +<br><a name="SEC13" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br> +<P> +Perl 5.10 introduced a feature whereby each alternative in a subpattern uses +the same numbers for its capturing parentheses. Such a subpattern starts with +(?| and is itself a non-capturing subpattern. For example, consider this +pattern: +<pre> + (?|(Sat)ur|(Sun))day +</pre> +Because the two alternatives are inside a (?| group, both sets of capturing +parentheses are numbered one. Thus, when the pattern matches, you can look +at captured substring number one, whichever alternative matched. This construct +is useful when you want to capture part, but not all, of one of a number of +alternatives. Inside a (?| group, parentheses are numbered as usual, but the +number is reset at the start of each branch. The numbers of any capturing +buffers that follow the subpattern start after the highest number used in any +branch. The following example is taken from the Perl documentation. +The numbers underneath show in which buffer the captured content will be +stored. +<pre> + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 +</pre> +A backreference or a recursive call to a numbered subpattern always refers to +the first one in the pattern with the given number. +</P> +<P> +An alternative approach to using this "branch reset" feature is to use +duplicate named subpatterns, as described in the next section. +</P> +<br><a name="SEC14" href="#TOC1">NAMED SUBPATTERNS</a><br> <P> Identifying capturing parentheses by number is simple, but it can be very hard to keep track of the numbers in complicated regular expressions. Furthermore, if an expression is modified, the numbers may change. To help with this -difficulty, PCRE supports the naming of subpatterns, something that Perl does -not provide. The Python syntax (?P<name>...) is used. References to capturing +difficulty, PCRE supports the naming of subpatterns. This feature was not +added to Perl until release 5.10. Python had the feature earlier, and PCRE +introduced it at release 4.0, using the Python syntax. PCRE now supports both +the Perl and the Python syntax. +</P> +<P> +In PCRE, a subpattern can be named in one of three ways: (?<name>...) or +(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing parentheses from other parts of the pattern, such as <a href="#backreferences">backreferences,</a> <a href="#recursion">recursion,</a> @@ -902,10 +1179,10 @@ </P> <P> Names consist of up to 32 alphanumeric characters and underscores. Named -capturing parentheses are still allocated numbers as well as names. The PCRE -API provides function calls for extracting the name-to-number translation table -from a compiled pattern. There is also a convenience function for extracting a -captured substring by name. +capturing parentheses are still allocated numbers as well as names, exactly as +if the names were not present. The PCRE API provides function calls for +extracting the name-to-number translation table from a compiled pattern. There +is also a convenience function for extracting a captured substring by name. </P> <P> By default, a name must be unique within a pattern, but it is possible to relax @@ -915,15 +1192,19 @@ abbreviation or as the full name, and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: <pre> - (?P<DN>Mon|Fri|Sun)(?:day)?| - (?P<DN>Tue)(?:sday)?| - (?P<DN>Wed)(?:nesday)?| - (?P<DN>Thu)(?:rsday)?| - (?P<DN>Sat)(?:urday)? + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? </pre> There are five capturing substrings, but only one is ever set after a match. +(An alternative way of solving this problem is to use a "branch reset" +subpattern, as described in the previous section.) +</P> +<P> The convenience function for extracting the data by name returns the substring -for the first, and in this example, the only, subpattern of that name that +for the first (and in this example, the only) subpattern of that name that matched. This saves searching to find which numbered subpattern it was. If you make a reference to a non-unique named subpattern from elsewhere in the pattern, the one that corresponds to the lowest number is used. For further @@ -931,15 +1212,21 @@ <a href="pcreapi.html"><b>pcreapi</b></a> documentation. </P> -<br><a name="SEC12" href="#TOC1">REPETITION</a><br> +<P> +<b>Warning:</b> You cannot use different names to distinguish between two +subpatterns with the same number (see the previous section) because PCRE uses +only the numbers when matching. +</P> +<br><a name="SEC15" href="#TOC1">REPETITION</a><br> <P> Repetition is specified by quantifiers, which can follow any of the following items: <pre> a literal data character - the . metacharacter + the dot metacharacter the \C escape sequence the \X escape sequence (in UTF-8 mode with Unicode properties) + the \R escape sequence an escape such as \d that matches a single character a character class a back reference (see next section) @@ -977,11 +1264,15 @@ </P> <P> The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. +previous item and the quantifier were not present. This may be useful for +subpatterns that are referenced as +<a href="#subpatternsassubroutines">subroutines</a> +from elsewhere in the pattern. Items other than subpatterns that have a {0} +quantifier are omitted from the compiled pattern. </P> <P> -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: +For convenience, the three most common quantifiers have single-character +abbreviations: <pre> * is equivalent to {0,} + is equivalent to {1,} @@ -1032,7 +1323,7 @@ way the rest of the pattern matches. </P> <P> -If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +If the PCRE_UNGREEDY option is set (an option that is not available in Perl), the quantifiers are not greedy by default, but individual ones can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. @@ -1044,7 +1335,7 @@ </P> <P> If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is implicitly anchored, because whatever follows will be tried against every character position in the subject string, so there is no point in retrying the overall match at any position after the first. PCRE normally treats such a @@ -1058,8 +1349,8 @@ <P> However, there is one situation where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail, and a later one -succeed. Consider, for example: +elsewhere in the pattern, a match at the start may fail where a later one +succeeds. Consider, for example: <pre> (.*)abc\1 </pre> @@ -1081,14 +1372,14 @@ </pre> matches "aba" the value of the second captured substring is "b". <a name="atomicgroup"></a></P> -<br><a name="SEC13" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> +<br><a name="SEC16" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> <P> -With both maximizing and minimizing repetition, failure of what follows -normally causes the repeated item to be re-evaluated to see if a different -number of repeats allows the rest of the pattern to match. Sometimes it is -useful to prevent this, either to change the nature of the match, or to cause -it fail earlier than it otherwise might, when the author of the pattern knows -there is no point in carrying on. +With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") +repetition, failure of what follows normally causes the repeated item to be +re-evaluated to see if a different number of repeats allows the rest of the +pattern to match. Sometimes it is useful to prevent this, either to change the +nature of the match, or to cause it fail earlier than it otherwise might, when +the author of the pattern knows there is no point in carrying on. </P> <P> Consider, for example, the pattern \d+foo when applied to the subject line @@ -1102,7 +1393,7 @@ that once a subpattern has matched, it is not to be re-evaluated in this way. </P> <P> -If we use atomic grouping for the previous example, the matcher would give up +If we use atomic grouping for the previous example, the matcher gives up immediately on failing to match "foo" the first time. The notation is a kind of special parenthesis, starting with (?> as in this example: <pre> @@ -1135,16 +1426,28 @@ <pre> \d++foo </pre> +Note that a possessive quantifier can be used with an entire group, for +example: +<pre> + (abc|xyz){2,3}+ +</pre> Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning or processing of a -possessive quantifier and the equivalent atomic group. +atomic group. However, there is no difference in the meaning of a possessive +quantifier and the equivalent atomic group, though there may be a performance +difference; possessive quantifiers should be slightly faster. </P> <P> -The possessive quantifier syntax is an extension to the Perl syntax. Jeffrey -Friedl originated the idea (and the name) in the first edition of his book. -Mike McCloskey liked it, so implemented it when he built Sun's Java package, -and PCRE copied it from there. +The possessive quantifier syntax is an extension to the Perl 5.8 syntax. +Jeffrey Friedl originated the idea (and the name) in the first edition of his +book. Mike McCloskey liked it, so implemented it when he built Sun's Java +package, and PCRE copied it from there. It ultimately found its way into Perl +at release 5.10. +</P> +<P> +PCRE has an optimization that automatically "possessifies" certain simple +pattern constructs. For example, the sequence A+B is treated as A++B because +there is no point in backtracking into a sequence of A's when B must follow. </P> <P> When a pattern contains an unlimited repeat inside a subpattern that can itself @@ -1173,7 +1476,7 @@ </pre> sequences of non-digits cannot be broken, and failure happens quickly. <a name="backreferences"></a></P> -<br><a name="SEC14" href="#TOC1">BACK REFERENCES</a><br> +<br><a name="SEC17" href="#TOC1">BACK REFERENCES</a><br> <P> Outside a character class, a backslash followed by a digit greater than 0 (and possibly further digits) is a back reference to a capturing subpattern earlier @@ -1190,12 +1493,37 @@ in an earlier iteration. </P> <P> -It is not possible to have a numerical "forward back reference" to subpattern -whose number is 10 or more. However, a back reference to any subpattern is -possible using named parentheses (see below). See also the subsection entitled +It is not possible to have a numerical "forward back reference" to a subpattern +whose number is 10 or more using this syntax because a sequence such as \50 is +interpreted as a character defined in octal. See the subsection entitled "Non-printing characters" <a href="#digitsafterbackslash">above</a> -for further details of the handling of digits following a backslash. +for further details of the handling of digits following a backslash. There is +no such problem when named parentheses are used. A back reference to any +subpattern is possible using named parentheses (see below). +</P> +<P> +Another way of avoiding the ambiguity inherent in the use of digits following a +backslash is to use the \g escape sequence, which is a feature introduced in +Perl 5.10. This escape must be followed by an unsigned number or a negative +number, optionally enclosed in braces. These examples are all identical: +<pre> + (ring), \1 + (ring), \g1 + (ring), \g{1} +</pre> +An unsigned number specifies an absolute reference without the ambiguity that +is present in the older syntax. It is also useful when literal digits follow +the reference. A negative number is a relative reference. Consider this +example: +<pre> + (abc(def)ghi)\g{-1} +</pre> +The sequence \g{-1} is a reference to the most recently started capturing +subpattern before \g, that is, is it equivalent to \2. Similarly, \g{-2} +would be equivalent to \1. The use of relative references can be helpful in +long patterns, and also in patterns that are created by joining together +fragments that contain references within themselves. </P> <P> A back reference matches whatever actually matched the capturing subpattern in @@ -1216,10 +1544,17 @@ capturing subpattern is matched caselessly. </P> <P> -Back references to named subpatterns use the Python syntax (?P=name). We could -rewrite the above example as follows: +There are several different ways of writing back references to named +subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or +\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified +back reference syntax, in which \g can be used for both numeric and named +references, is also supported. We could rewrite the above example in any of +the following ways: <pre> + (?<p1>(?i)rah)\s+\k<p1> + (?'p1'(?i)rah)\s+\k{p1} (?P<p1>(?i)rah)\s+(?P=p1) + (?<p1>(?i)rah)\s+\g{p1} </pre> A subpattern that is referenced by name may appear in the pattern before or after the reference. @@ -1255,7 +1590,7 @@ done using alternation, as in the example above, or by a quantifier with a minimum of zero. <a name="bigassertions"></a></P> -<br><a name="SEC15" href="#TOC1">ASSERTIONS</a><br> +<br><a name="SEC18" href="#TOC1">ASSERTIONS</a><br> <P> An assertion is a test on the characters following or preceding the current matching point that does not actually consume any characters. The simple @@ -1337,21 +1672,27 @@ <pre> (?<=abc|abde) </pre> +In some cases, the Perl 5.10 escape sequence \K +<a href="#resetmatchstart">(see above)</a> +can be used instead of a lookbehind assertion; this is not restricted to a +fixed-length. +</P> +<P> The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed width and then try to +temporarily move the current position back by the fixed length and then try to match. If there are insufficient characters before the current position, the -match is deemed to fail. +assertion fails. </P> <P> PCRE does not allow the \C escape (which matches a single byte in UTF-8 mode) to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. The \X escape, which can match different numbers -of bytes, is also not permitted. +the length of the lookbehind. The \X and \R escapes, which can match +different numbers of bytes, are also not permitted. </P> <P> -Atomic groups can be used in conjunction with lookbehind assertions to specify -efficient matching at the end of the subject string. Consider a simple pattern -such as +Possessive quantifiers can be used in conjunction with lookbehind assertions to +specify efficient matching at the end of the subject string. Consider a simple +pattern such as <pre> abcd$ </pre> @@ -1367,13 +1708,9 @@ covers the entire string, from right to left, so we are no better off. However, if the pattern is written as <pre> - ^(?>.*)(?<=abcd) -</pre> -or, equivalently, using the possessive quantifier syntax, -<pre> ^.*+(?<=abcd) </pre> -there can be no backtracking for the .* item; it can match only the entire +there can be no backtracking for the .*+ item; it can match only the entire string. The subsequent lookbehind assertion does a single test on the last four characters. If it fails, the match fails immediately. For long strings, this approach makes a significant difference to the processing time. @@ -1413,7 +1750,7 @@ is another pattern that matches "foo" preceded by three digits and any three characters that are not "999". <a name="conditions"></a></P> -<br><a name="SEC16" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> +<br><a name="SEC19" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> <P> It is possible to cause the matching process to obey a subpattern conditionally or to choose between two alternative subpatterns, depending on @@ -1428,15 +1765,20 @@ subpattern, a compile-time error occurs. </P> <P> -There are three kinds of condition. If the text between the parentheses -consists of a sequence of digits, or a sequence of alphanumeric characters and -underscores, the condition is satisfied if the capturing subpattern of that -number or name has previously matched. There is a possible ambiguity here, -because subpattern names may consist entirely of digits. PCRE looks first for a -named subpattern; if it cannot find one and the text consists entirely of -digits, it looks for a subpattern of that number, which must be greater than -zero. Using subpattern names that consist entirely of digits is not -recommended. +There are four kinds of condition: references to subpatterns, references to +recursion, a pseudo-condition called DEFINE, and assertions. +</P> +<br><b> +Checking for a used subpattern by number +</b><br> +<P> +If the text between the parentheses consists of a sequence of digits, the +condition is true if the capturing subpattern of that number has previously +matched. An alternative notation is to precede the digits with a plus or minus +sign. In this case, the subpattern number is relative rather than absolute. +The most recently opened parentheses can be referenced by (?(-1), the next most +recent by (?(-2), and so on. In looping constructs it can also make sense to +refer to subsequent groups with constructs such as (?(+2). </P> <P> Consider the following pattern, which contains non-significant white space to @@ -1453,18 +1795,85 @@ the condition is true, and so the yes-pattern is executed and a closing parenthesis is required. Otherwise, since no-pattern is not present, the subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. Rewriting it to use a -named subpattern gives this: +non-parentheses, optionally enclosed in parentheses. +</P> +<P> +If you were embedding this pattern in a larger one, you could use a relative +reference: <pre> - (?P<OPEN> \( )? [^()]+ (?(OPEN) \) ) + ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... </pre> +This makes the fragment independent of the parentheses in the larger pattern. +</P> +<br><b> +Checking for a used subpattern by name +</b><br> +<P> +Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used +subpattern by name. For compatibility with earlier versions of PCRE, which had +this facility before Perl, the syntax (?(name)...) is also recognized. However, +there is a possible ambiguity with this syntax, because subpattern names may +consist entirely of digits. PCRE looks first for a named subpattern; if it +cannot find one and the name consists entirely of digits, PCRE looks for a +subpattern of that number, which must be greater than zero. Using subpattern +names that consist entirely of digits is not recommended. +</P> +<P> +Rewriting the above example to use a named subpattern gives this: +<pre> + (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) + +</PRE> +</P> +<br><b> +Checking for pattern recursion +</b><br> +<P> If the condition is the string (R), and there is no subpattern with the name R, -the condition is satisfied if a recursive call to the pattern or subpattern has -been made. At "top level", the condition is false. This is a PCRE extension. -Recursive patterns are described in the next section. +the condition is true if a recursive call to the whole pattern or any +subpattern has been made. If digits or a name preceded by ampersand follow the +letter R, for example: +<pre> + (?(R3)...) or (?(R&name)...) +</pre> +the condition is true if the most recent recursion is into the subpattern whose +number or name is given. This condition does not check the entire recursion +stack. +</P> +<P> +At "top level", all these recursion test conditions are false. Recursive +patterns are described below. </P> +<br><b> +Defining subpatterns for use by reference only +</b><br> <P> -If the condition is not a sequence of digits or (R), it must be an assertion. +If the condition is the string (DEFINE), and there is no subpattern with the +name DEFINE, the condition is always false. In this case, there may be only one +alternative in the subpattern. It is always skipped if control reaches this +point in the pattern; the idea of DEFINE is that it can be used to define +"subroutines" that can be referenced from elsewhere. (The use of "subroutines" +is described below.) For example, a pattern to match an IPv4 address could be +written like this (ignore whitespace and line breaks): +<pre> + (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) + \b (?&byte) (\.(?&byte)){3} \b +</pre> +The first part of the pattern is a DEFINE group inside which a another group +named "byte" is defined. This matches an individual component of an IPv4 +address (a number less than 256). When matching takes place, this part of the +pattern is skipped because DEFINE acts like a false condition. +</P> +<P> +The rest of the pattern uses references to the named group to match the four +dot-separated components of an IPv4 address, insisting on a word boundary at +each end. +</P> +<br><b> +Assertion conditions +</b><br> +<P> +If the condition is not in any of the above formats, it must be an assertion. This may be a positive or negative lookahead or lookbehind assertion. Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: @@ -1479,7 +1888,7 @@ against the second. This pattern matches strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. <a name="comments"></a></P> -<br><a name="SEC17" href="#TOC1">COMMENTS</a><br> +<br><a name="SEC20" href="#TOC1">COMMENTS</a><br> <P> The sequence (?# marks the start of a comment that continues up to the next closing parenthesis. Nested parentheses are not permitted. The characters @@ -1490,35 +1899,43 @@ character class introduces a comment that continues to immediately after the next newline in the pattern. <a name="recursion"></a></P> -<br><a name="SEC18" href="#TOC1">RECURSIVE PATTERNS</a><br> +<br><a name="SEC21" href="#TOC1">RECURSIVE PATTERNS</a><br> <P> Consider the problem of matching a string in parentheses, allowing for unlimited nested parentheses. Without the use of recursion, the best that can be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. Perl provides a facility -that allows regular expressions to recurse (amongst other things). It does this -by interpolating Perl code in the expression at run time, and the code can -refer to the expression itself. A Perl pattern to solve the parentheses problem -can be created like this: +is not possible to handle an arbitrary nesting depth. +</P> +<P> +For some time, Perl has provided a facility that allows regular expressions to +recurse (amongst other things). It does this by interpolating Perl code in the +expression at run time, and the code can refer to the expression itself. A Perl +pattern using code interpolation to solve the parentheses problem can be +created like this: <pre> $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; </pre> The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. Obviously, PCRE cannot support -the interpolation of Perl code. Instead, it supports some special syntax for -recursion of the entire pattern, and also for individual subpattern recursion. +recursively to the pattern in which it appears. +</P> +<P> +Obviously, PCRE cannot support the interpolation of Perl code. Instead, it +supports special syntax for recursion of the entire pattern, and also for +individual subpattern recursion. After its introduction in PCRE and Python, +this kind of recursion was introduced into Perl at release 5.10. </P> <P> -The special item that consists of (? followed by a number greater than zero and -a closing parenthesis is a recursive call of the subpattern of the given -number, provided that it occurs inside that subpattern. (If not, it is a -"subroutine" call, which is described in the next section.) The special item -(?R) is a recursive call of the entire regular expression. +A special item that consists of (? followed by a number greater than zero and a +closing parenthesis is a recursive call of the subpattern of the given number, +provided that it occurs inside that subpattern. (If not, it is a "subroutine" +call, which is described in the next section.) The special item (?R) or (?0) is +a recursive call of the entire regular expression. </P> <P> -A recursive subpattern call is always treated as an atomic group. That is, once -it has matched some of the subject string, it is never re-entered, even if -it contains untried alternatives and there is a subsequent matching failure. +In PCRE (like Python, but unlike Perl), a recursive subpattern call is always +treated as an atomic group. That is, once it has matched some of the subject +string, it is never re-entered, even if it contains untried alternatives and +there is a subsequent matching failure. </P> <P> This PCRE pattern solves the nested parentheses problem (assume the @@ -1538,18 +1955,37 @@ ( \( ( (?>[^()]+) | (?1) )* \) ) </pre> We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. In a larger pattern, keeping track of -parenthesis numbers can be tricky. It may be more convenient to use named -parentheses instead. For this, PCRE uses (?P>name), which is an extension to -the Python syntax that PCRE uses for named parentheses (Perl does not provide -named parentheses). We could rewrite the above example as follows: -<pre> - (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) ) -</pre> -This particular example pattern contains nested unlimited repeats, and so the -use of atomic grouping for matching strings of non-parentheses is important -when applying the pattern to strings that do not match. For example, when this -pattern is applied to +them instead of the whole pattern. +</P> +<P> +In a larger pattern, keeping track of parenthesis numbers can be tricky. This +is made easier by the use of relative references. (A Perl 5.10 feature.) +Instead of (?1) in the pattern above you can write (?-2) to refer to the second +most recently opened parentheses preceding the recursion. In other words, a +negative number counts capturing parentheses leftwards from the point at which +it is encountered. +</P> +<P> +It is also possible to refer to subsequently opened parentheses, by writing +references such as (?+2). However, these cannot be recursive because the +reference is not inside the parentheses that are referenced. They are always +"subroutine" calls, as described in the next section. +</P> +<P> +An alternative approach is to use named parentheses instead. The Perl syntax +for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We +could rewrite the above example as follows: +<pre> + (?<pn> \( ( (?>[^()]+) | (?&pn) )* \) ) +</pre> +If there is more than one subpattern with the same name, the earliest one is +used. +</P> +<P> +This particular example pattern that we have been looking at contains nested +unlimited repeats, and so the use of atomic grouping for matching strings of +non-parentheses is important when applying the pattern to strings that do not +match. For example, when this pattern is applied to <pre> (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() </pre> @@ -1562,7 +1998,7 @@ At the end of a match, the values set for any capturing subpatterns are those from the outermost level of the recursion at which the subpattern value is set. If you want to obtain intermediate values, a callout function can be used (see -the next section and the +below and the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation). If the pattern above is matched against <pre> @@ -1593,12 +2029,19 @@ different alternatives for the recursive and non-recursive cases. The (?R) item is the actual recursive call. <a name="subpatternsassubroutines"></a></P> -<br><a name="SEC19" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> +<br><a name="SEC22" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> <P> If the syntax for a recursive subpattern reference (either by number or by name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. An earlier example pointed out that the -pattern +subroutine in a programming language. The "called" subpattern may be defined +before or after the reference. A numbered reference can be absolute or +relative, as in these examples: +<pre> + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... +</pre> +An earlier example pointed out that the pattern <pre> (sens|respons)e and \1ibility </pre> @@ -1608,8 +2051,7 @@ (sens|respons)e and (?1)ibility </pre> is used, it does match "sense and responsibility" as well as the other two -strings. Such references, if given numerically, must follow the subpattern to -which they refer. However, named references can refer to later subpatterns. +strings. Another example is given in the discussion of DEFINE above. </P> <P> Like recursive subpatterns, a "subroutine" call is always treated as an atomic @@ -1617,7 +2059,35 @@ re-entered, even if it contains untried alternatives and there is a subsequent matching failure. </P> -<br><a name="SEC20" href="#TOC1">CALLOUTS</a><br> +<P> +When a subpattern is used as a subroutine, processing options such as +case-independence are fixed when the subpattern is defined. They cannot be +changed for different calls. For example, consider this pattern: +<pre> + (abc)(?i:(?-1)) +</pre> +It matches "abcabc". It does not match "abcABC" because the change of +processing option does not affect the called subpattern. +<a name="onigurumasubroutines"></a></P> +<br><a name="SEC23" href="#TOC1">ONIGURUMA SUBROUTINE SYNTAX</a><br> +<P> +For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a subroutine, possibly recursively. Here +are two of the examples used above, rewritten using this syntax: +<pre> + (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) + (sens|respons)e and \g'1'ibility +</pre> +PCRE supports an extension to Oniguruma: if a number is preceded by a +plus or a minus sign it is taken as a relative reference. For example: +<pre> + (abc)(?i:\g<-1>) +</pre> +Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i> +synonymous. The former is a back reference; the latter is a subroutine call. +</P> +<br><a name="SEC24" href="#TOC1">CALLOUTS</a><br> <P> Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl code to be obeyed in the middle of matching a regular expression. This makes it @@ -1636,7 +2106,7 @@ can put a number less than 256 after the letter C. The default value is zero. For example, this pattern has two callout points: <pre> - (?C1)\dabc(?C2)def + (?C1)abc(?C2)def </pre> If the PCRE_AUTO_CALLOUT flag is passed to <b>pcre_compile()</b>, callouts are automatically installed before each item in the pattern. They are all numbered @@ -1652,10 +2122,141 @@ <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. </P> +<br><a name="SEC25" href="#TOC1">BACKTRACKING CONTROL</a><br> +<P> +Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which +are described in the Perl documentation as "experimental and subject to change +or removal in a future version of Perl". It goes on to say: "Their usage in +production code should be noted to avoid problems during upgrades." The same +remarks apply to the PCRE features described in this section. +</P> +<P> +Since these verbs are specifically related to backtracking, most of them can be +used only when the pattern is to be matched using <b>pcre_exec()</b>, which uses +a backtracking algorithm. With the exception of (*FAIL), which behaves like a +failing negative assertion, they cause an error if encountered by +<b>pcre_dfa_exec()</b>. +</P> +<P> +The new verbs make use of what was previously invalid syntax: an opening +parenthesis followed by an asterisk. In Perl, they are generally of the form +(*VERB:ARG) but PCRE does not support the use of arguments, so its general +form is just (*VERB). Any number of these verbs may occur in a pattern. There +are two kinds: +</P> +<br><b> +Verbs that act immediately +</b><br> +<P> +The following verbs act as soon as they are encountered: +<pre> + (*ACCEPT) +</pre> +This verb causes the match to end successfully, skipping the remainder of the +pattern. When inside a recursion, only the innermost pattern is ended +immediately. PCRE differs from Perl in what happens if the (*ACCEPT) is inside +capturing parentheses. In Perl, the data so far is captured: in PCRE no data is +captured. For example: +<pre> + A(A|B(*ACCEPT)|C)D +</pre> +This matches "AB", "AAD", or "ACD", but when it matches "AB", no data is +captured. +<pre> + (*FAIL) or (*F) +</pre> +This verb causes the match to fail, forcing backtracking to occur. It is +equivalent to (?!) but easier to read. The Perl documentation notes that it is +probably useful only when combined with (?{}) or (??{}). Those are, of course, +Perl features that are not present in PCRE. The nearest equivalent is the +callout feature, as for example in this pattern: +<pre> + a+(?C)(*FAIL) +</pre> +A match with the string "aaaa" always fails, but the callout is taken before +each backtrack happens (in this example, 10 times). +</P> +<br><b> +Verbs that act after backtracking +</b><br> <P> -Last updated: 06 June 2006 +The following verbs do nothing when they are encountered. Matching continues +with what follows, but if there is no subsequent match, a failure is forced. +The verbs differ in exactly what kind of failure occurs. +<pre> + (*COMMIT) +</pre> +This verb causes the whole match to fail outright if the rest of the pattern +does not match. Even if the pattern is unanchored, no further attempts to find +a match by advancing the start point take place. Once (*COMMIT) has been +passed, <b>pcre_exec()</b> is committed to finding a match at the current +starting point, or not at all. For example: +<pre> + a+(*COMMIT)b +</pre> +This matches "xxaab" but not "aacaab". It can be thought of as a kind of +dynamic anchor, or "I've started, so I must finish." +<pre> + (*PRUNE) +</pre> +This verb causes the match to fail at the current position if the rest of the +pattern does not match. If the pattern is unanchored, the normal "bumpalong" +advance to the next starting character then happens. Backtracking can occur as +usual to the left of (*PRUNE), or when matching to the right of (*PRUNE), but +if there is no match to the right, backtracking cannot cross (*PRUNE). +In simple cases, the use of (*PRUNE) is just an alternative to an atomic +group or possessive quantifier, but there are some uses of (*PRUNE) that cannot +be expressed in any other way. +<pre> + (*SKIP) +</pre> +This verb is like (*PRUNE), except that if the pattern is unanchored, the +"bumpalong" advance is not to the next character, but to the position in the +subject where (*SKIP) was encountered. (*SKIP) signifies that whatever text +was matched leading up to it cannot be part of a successful match. Consider: +<pre> + a+(*SKIP)b +</pre> +If the subject is "aaaac...", after the first match attempt fails (starting at +the first character in the string), the starting point skips on to start the +next attempt at "c". Note that a possessive quantifer does not have the same +effect in this example; although it would suppress backtracking during the +first match attempt, the second attempt would start at the second character +instead of skipping on to "c". +<pre> + (*THEN) +</pre> +This verb causes a skip to the next alternation if the rest of the pattern does +not match. That is, it cancels pending backtracking, but only within the +current alternation. Its name comes from the observation that it can be used +for a pattern-based if-then-else block: +<pre> + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... +</pre> +If the COND1 pattern matches, FOO is tried (and possibly further items after +the end of the group if FOO succeeds); on failure the matcher skips to the +second alternative and tries COND2, without backtracking into COND1. If (*THEN) +is used outside of any alternation, it acts exactly like (*PRUNE). +</P> +<br><a name="SEC26" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3), <b>pcre</b>(3). +</P> +<br><a name="SEC27" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC28" href="#TOC1">REVISION</a><br> +<P> +Last updated: 11 April 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcreperform.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcreperform.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcreperform.html Mon Jun 8 18:51:30 2009 @@ -16,13 +16,73 @@ PCRE PERFORMANCE </b><br> <P> -Certain items that may appear in regular expression patterns are more efficient +Two aspects of performance are discussed below: memory usage and processing +time. The way you express your pattern as a regular expression can affect both +of them. +</P> +<br><b> +MEMORY USAGE +</b><br> +<P> +Patterns are compiled by PCRE into a reasonably efficient byte code, so that +most simple patterns do not use much memory. However, there is one case where +memory usage can be unexpectedly large. When a parenthesized subpattern has a +quantifier with a minimum greater than 1 and/or a limited maximum, the whole +subpattern is repeated in the compiled code. For example, the pattern +<pre> + (abc|def){2,4} +</pre> +is compiled as if it were +<pre> + (abc|def)(abc|def)((abc|def)(abc|def)?)? +</pre> +(Technical aside: It is done this way so that backtrack points within each of +the repetitions can be independently maintained.) +</P> +<P> +For regular expressions whose quantifiers use only small numbers, this is not +usually a problem. However, if the numbers are large, and particularly if such +repetitions are nested, the memory usage can become an embarrassment. For +example, the very simple pattern +<pre> + ((ab){1,1000}c){1,3} +</pre> +uses 51K bytes when compiled. When PCRE is compiled with its default internal +pointer size of two bytes, the size limit on a compiled pattern is 64K, and +this is reached with the above pattern if the outer repetition is increased +from 3 to 4. PCRE can be compiled to use larger internal pointers and thus +handle larger compiled patterns, but it is better to try to rewrite your +pattern to use less memory if you can. +</P> +<P> +One way of reducing the memory usage for such patterns is to make use of PCRE's +<a href="pcrepattern.html#subpatternsassubroutines">"subroutine"</a> +facility. Re-writing the above pattern as +<pre> + ((ab)(?2){0,999}c)(?1){0,2} +</pre> +reduces the memory requirements to 18K, and indeed it remains under 20K even +with the outer repetition increased to 100. However, this pattern is not +exactly equivalent, because the "subroutine" calls are treated as +<a href="pcrepattern.html#atomicgroup">atomic groups</a> +into which there can be no backtracking if there is a subsequent matching +failure. Therefore, PCRE cannot do this kind of rewriting automatically. +Furthermore, there is a noticeable loss of speed when executing the modified +pattern. Nevertheless, if the atomic grouping is not a problem and the loss of +speed is acceptable, this kind of rewriting will allow you to process patterns +that PCRE cannot otherwise handle. +</P> +<br><b> +PROCESSING TIME +</b><br> +<P> +Certain items in regular expression patterns are processed more efficiently than others. It is more efficient to use a character class like [aeiou] than a -set of alternatives such as (a|e|i|o|u). In general, the simplest construction -that provides the required behaviour is usually the most efficient. Jeffrey -Friedl's book contains a lot of useful general discussion about optimizing -regular expressions for efficient performance. This document contains a few -observations about PCRE. +set of single-character alternatives such as (a|e|i|o|u). In general, the +simplest construction that provides the required behaviour is usually the most +efficient. Jeffrey Friedl's book contains a lot of useful general discussion +about optimizing regular expressions for efficient performance. This document +contains a few observations about PCRE. </P> <P> Using Unicode character properties (the \p, \P, and \X escapes) is slow, @@ -58,14 +118,15 @@ long time to run when applied to a string that does not match. Consider the pattern fragment <pre> - (a+)* + ^(a+)* </pre> -This can match "aaaa" in 33 different ways, and this number increases very +This can match "aaaa" in 16 different ways, and this number increases very rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match +times, and for each of those cases other than 0 or 4, the + repeats can match different numbers of times.) When the remainder of the pattern is such that the entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. +variation, and this can take an extremely long time, even for relatively short +strings. </P> <P> An optimization catches some of the more simple cases such as @@ -88,10 +149,25 @@ In many cases, the solution to this kind of performance issue is to use an atomic group or a possessive quantifier. </P> +<br><b> +AUTHOR +</b><br> <P> -Last updated: 28 February 2005 +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 06 March 2007 +<br> +Copyright © 1997-2007 University of Cambridge. <br> -Copyright © 1997-2005 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcreposix.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcreposix.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcreposix.html Mon Jun 8 18:51:30 2009 @@ -21,6 +21,7 @@ <li><a name="TOC6" href="#SEC6">ERROR MESSAGES</a> <li><a name="TOC7" href="#SEC7">MEMORY USAGE</a> <li><a name="TOC8" href="#SEC8">AUTHOR</a> +<li><a name="TOC9" href="#SEC9">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">SYNOPSIS OF POSIX API</a><br> <P> @@ -58,11 +59,11 @@ call the native ones, it is also necessary to add <b>-lpcre</b>. </P> <P> -I have implemented only those option bits that can be reasonably mapped to PCRE -native options. In addition, the option REG_EXTENDED is defined with the value -zero. This has no effect, but since programs that are written to the POSIX -interface often use it, this makes it easier to slot in PCRE as a replacement -library. Other POSIX options are not even defined. +I have implemented only those POSIX option bits that can be reasonably mapped +to PCRE native options. In addition, the option REG_EXTENDED is defined with +the value zero. This has no effect, but since programs that are written to the +POSIX interface often use it, this makes it easier to slot in PCRE as a +replacement library. Other POSIX options are not even defined. </P> <P> When PCRE is called via these functions, it is only the API that is POSIX-like @@ -179,18 +180,36 @@ <br><a name="SEC5" href="#TOC1">MATCHING A PATTERN</a><br> <P> The function <b>regexec()</b> is called to match a compiled pattern <i>preg</i> -against a given <i>string</i>, which is terminated by a zero byte, subject to -the options in <i>eflags</i>. These can be: +against a given <i>string</i>, which is by default terminated by a zero byte +(but see REG_STARTEND below), subject to the options in <i>eflags</i>. These can +be: <pre> REG_NOTBOL </pre> The PCRE_NOTBOL option is set when calling the underlying PCRE matching function. <pre> + REG_NOTEMPTY +</pre> +The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching +function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, +setting this option can give more POSIX-like behaviour in some situations. +<pre> REG_NOTEOL </pre> The PCRE_NOTEOL option is set when calling the underlying PCRE matching function. +<pre> + REG_STARTEND +</pre> +The string is considered to start at <i>string</i> + <i>pmatch[0].rm_so</i> and +to have a terminating NUL located at <i>string</i> + <i>pmatch[0].rm_eo</i> +(there need not actually be a NUL at that location), regardless of the value of +<i>nmatch</i>. This is a BSD extension, compatible with but not specified by +IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software +intended to be portable to other systems. Note that a non-zero <i>rm_so</i> does +not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not +how it is matched. </P> <P> If the pattern was compiled with the REG_NOSUB flag, no data about any matched @@ -231,14 +250,17 @@ <P> Philip Hazel <br> -University Computing Service, +University Computing Service +<br> +Cambridge CB2 3QH, England. <br> -Cambridge CB2 3QG, England. </P> +<br><a name="SEC9" href="#TOC1">REVISION</a><br> <P> -Last updated: 16 January 2006 +Last updated: 11 March 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcreprecompile.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcreprecompile.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcreprecompile.html Mon Jun 8 18:51:30 2009 @@ -17,6 +17,8 @@ <li><a name="TOC2" href="#SEC2">SAVING A COMPILED PATTERN</a> <li><a name="TOC3" href="#SEC3">RE-USING A PRECOMPILED PATTERN</a> <li><a name="TOC4" href="#SEC4">COMPATIBILITY WITH DIFFERENT PCRE RELEASES</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">SAVING AND RE-USING PRECOMPILED PCRE PATTERNS</a><br> <P> @@ -32,7 +34,9 @@ If you save compiled patterns to a file, you can copy them to a different host and run them there. This works even if the new host has the opposite endianness to the one on which the patterns were compiled. There may be a small -performance penalty, but it should be insignificant. +performance penalty, but it should be insignificant. However, compiling regular +expressions with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes. </P> <br><a name="SEC2" href="#TOC1">SAVING A COMPILED PATTERN</a><br> <P> @@ -120,21 +124,25 @@ </P> <br><a name="SEC4" href="#TOC1">COMPATIBILITY WITH DIFFERENT PCRE RELEASES</a><br> <P> -The layout of the control block that is at the start of the data that makes up -a compiled pattern was changed for release 5.0. If you have any saved patterns -that were compiled with previous releases (not a facility that was previously -advertised), you will have to recompile them for release 5.0. However, from now -on, it should be possible to make changes in a compatible manner. +In general, it is safest to recompile all saved patterns when you update to a +new PCRE release, though not all updates actually require this. Recompiling is +definitely needed for release 7.2. </P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> <P> -Notwithstanding the above, if you have any saved patterns in UTF-8 mode that -use \p or \P that were compiled with any release up to and including 6.4, you -will have to recompile them for release 6.5 and above. +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> </P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> <P> -Last updated: 01 February 2006 +Last updated: 13 June 2007 +<br> +Copyright © 1997-2007 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcresample.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcresample.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcresample.html Mon Jun 8 18:51:30 2009 @@ -72,10 +72,25 @@ </pre> (for example) to the compile command to get round this problem. </P> +<br><b> +AUTHOR +</b><br> <P> -Last updated: 09 September 2004 +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 23 January 2008 +<br> +Copyright © 1997-2008 University of Cambridge. <br> -Copyright © 1997-2004 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcrestack.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcrestack.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcrestack.html Mon Jun 8 18:51:30 2009 @@ -63,7 +63,7 @@ required. Consider now this rewritten pattern, which matches exactly the same strings: <pre> - ([^<]++|<(?!inet)) + ([^<]++|<(?!inet))+ </pre> This uses very much less stack, because runs of characters that do not contain "<" are "swallowed" in one item inside the parentheses. Recursion happens only @@ -73,23 +73,62 @@ stack usage. </P> <P> +This example shows that one way of avoiding stack problems when matching long +subject strings is to write repeated parenthesized subpatterns to match more +than one character whenever possible. +</P> +<br><b> +Compiling PCRE to use heap instead of stack +</b><br> +<P> In environments where stack memory is constrained, you might want to compile PCRE to use heap memory instead of stack for remembering back-up points. This makes it run a lot more slowly, however. Details of how to do this are given in the <a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation. When built in this way, instead of using the stack, PCRE obtains +and frees memory by calling the functions that are pointed to by the +<b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> variables. By default, these +point to <b>malloc()</b> and <b>free()</b>, but you can replace the pointers to +cause PCRE to use your own functions. Since the block sizes are always the +same, and are always freed in reverse order, it may be possible to implement +customized memory handlers that are more efficient than the standard functions. +</P> +<br><b> +Limiting PCRE's stack usage +</b><br> +<P> +PCRE has an internal counter that can be used to limit the depth of recursion, +and thus cause <b>pcre_exec()</b> to give an error code before it runs out of +stack. By default, the limit is very large, and unlikely ever to operate. It +can be changed when PCRE is built, and it can also be set when +<b>pcre_exec()</b> is called. For details of these interfaces, see the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +and +<a href="pcreapi.html"><b>pcreapi</b></a> documentation. </P> <P> -In Unix-like environments, there is not often a problem with the stack, though -the default limit on stack size varies from system to system. Values from 8Mb -to 64Mb are common. You can find your default limit by running the command: +As a very rough rule of thumb, you should reckon on about 500 bytes per +recursion. Thus, if you want to limit your stack usage to 8Mb, you +should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can +support around 128000 recursions. The <b>pcretest</b> test program has a command +line option (<b>-S</b>) that can be used to increase the size of its stack. +</P> +<br><b> +Changing stack size in Unix-like systems +</b><br> +<P> +In Unix-like environments, there is not often a problem with the stack unless +very long strings are involved, though the default limit on stack size varies +from system to system. Values from 8Mb to 64Mb are common. You can find your +default limit by running the command: <pre> ulimit -s </pre> -The effect of running out of stack is often SIGSEGV, though sometimes an error -message is given. You can normally increase the limit on stack size by code -such as this: +Unfortunately, the effect of running out of stack is often SIGSEGV, though +sometimes a more explicit error message is given. You can normally increase the +limit on stack size by code such as this: <pre> struct rlimit rlim; getrlimit(RLIMIT_STACK, &rlim); @@ -100,28 +139,34 @@ attempts to increase the soft limit to 100Mb using <b>setrlimit()</b>. You must do this before calling <b>pcre_exec()</b>. </P> +<br><b> +Changing stack size in Mac OS X +</b><br> <P> -PCRE has an internal counter that can be used to limit the depth of recursion, -and thus cause <b>pcre_exec()</b> to give an error code before it runs out of -stack. By default, the limit is very large, and unlikely ever to operate. It -can be changed when PCRE is built, and it can also be set when -<b>pcre_exec()</b> is called. For details of these interfaces, see the -<a href="pcrebuild.html"><b>pcrebuild</b></a> -and -<a href="pcreapi.html"><b>pcreapi</b></a> -documentation. +Using <b>setrlimit()</b>, as described above, should also work on Mac OS X. It +is also possible to set a stack size when linking a program. There is a +discussion about stack sizes in Mac OS X at this web site: +<a href="http://developer.apple.com/qa/qa2005/qa1419.html">http://developer.apple.com/qa/qa2005/qa1419.html.</a> </P> +<br><b> +AUTHOR +</b><br> <P> -As a very rough rule of thumb, you should reckon on about 500 bytes per -recursion. Thus, if you want to limit your stack usage to 8Mb, you -should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can -support around 128000 recursions. The <b>pcretest</b> test program has a command -line option (<b>-S</b>) that can be used to increase its stack. +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> </P> +<br><b> +REVISION +</b><br> <P> -Last updated: 29 June 2006 +Last updated: 09 July 2008 +<br> +Copyright © 1997-2008 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Added: freeswitch/trunk/libs/pcre/doc/html/pcresyntax.html ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/html/pcresyntax.html Mon Jun 8 18:51:30 2009 @@ -0,0 +1,473 @@ +<html> +<head> +<title>pcresyntax specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcresyntax man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a> +<li><a name="TOC2" href="#SEC2">QUOTING</a> +<li><a name="TOC3" href="#SEC3">CHARACTERS</a> +<li><a name="TOC4" href="#SEC4">CHARACTER TYPES</a> +<li><a name="TOC5" href="#SEC5">GENERAL CATEGORY PROPERTY CODES FOR \p and \P</a> +<li><a name="TOC6" href="#SEC6">SCRIPT NAMES FOR \p AND \P</a> +<li><a name="TOC7" href="#SEC7">CHARACTER CLASSES</a> +<li><a name="TOC8" href="#SEC8">QUANTIFIERS</a> +<li><a name="TOC9" href="#SEC9">ANCHORS AND SIMPLE ASSERTIONS</a> +<li><a name="TOC10" href="#SEC10">MATCH POINT RESET</a> +<li><a name="TOC11" href="#SEC11">ALTERNATION</a> +<li><a name="TOC12" href="#SEC12">CAPTURING</a> +<li><a name="TOC13" href="#SEC13">ATOMIC GROUPS</a> +<li><a name="TOC14" href="#SEC14">COMMENT</a> +<li><a name="TOC15" href="#SEC15">OPTION SETTING</a> +<li><a name="TOC16" href="#SEC16">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a> +<li><a name="TOC17" href="#SEC17">BACKREFERENCES</a> +<li><a name="TOC18" href="#SEC18">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a> +<li><a name="TOC19" href="#SEC19">CONDITIONAL PATTERNS</a> +<li><a name="TOC20" href="#SEC20">BACKTRACKING CONTROL</a> +<li><a name="TOC21" href="#SEC21">NEWLINE CONVENTIONS</a> +<li><a name="TOC22" href="#SEC22">WHAT \R MATCHES</a> +<li><a name="TOC23" href="#SEC23">CALLOUTS</a> +<li><a name="TOC24" href="#SEC24">SEE ALSO</a> +<li><a name="TOC25" href="#SEC25">AUTHOR</a> +<li><a name="TOC26" href="#SEC26">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a><br> +<P> +The full syntax and semantics of the regular expressions that are supported by +PCRE are described in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. This document contains just a quick-reference summary of the +syntax. +</P> +<br><a name="SEC2" href="#TOC1">QUOTING</a><br> +<P> +<pre> + \x where x is non-alphanumeric is a literal x + \Q...\E treat enclosed characters as literal +</PRE> +</P> +<br><a name="SEC3" href="#TOC1">CHARACTERS</a><br> +<P> +<pre> + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any character + \e escape (hex 1B) + \f formfeed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \ddd character with octal code ddd, or backreference + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. +</PRE> +</P> +<br><a name="SEC4" href="#TOC1">CHARACTER TYPES</a><br> +<P> +<pre> + . any character except newline; + in dotall mode, any character whatsoever + \C one byte, even in UTF-8 mode (best avoided) + \d a decimal digit + \D a character that is not a decimal digit + \h a horizontal whitespace character + \H a character that is not a horizontal whitespace character + \p{<i>xx</i>} a character with the <i>xx</i> property + \P{<i>xx</i>} a character without the <i>xx</i> property + \R a newline sequence + \s a whitespace character + \S a character that is not a whitespace character + \v a vertical whitespace character + \V a character that is not a vertical whitespace character + \w a "word" character + \W a "non-word" character + \X an extended Unicode sequence +</pre> +In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters. +</P> +<br><a name="SEC5" href="#TOC1">GENERAL CATEGORY PROPERTY CODES FOR \p and \P</a><br> +<P> +<pre> + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +</PRE> +</P> +<br><a name="SEC6" href="#TOC1">SCRIPT NAMES FOR \p AND \P</a><br> +<P> +Arabic, +Armenian, +Balinese, +Bengali, +Bopomofo, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Inherited, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lycian, +Lydian, +Malayalam, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Saurashtra, +Shavian, +Sinhala, +Sudanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +</P> +<br><a name="SEC7" href="#TOC1">CHARACTER CLASSES</a><br> +<P> +<pre> + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set + + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space whitespace + upper upper case letter + word same as \w + xdigit hexadecimal digit +</pre> +In PCRE, POSIX character set names recognize only ASCII characters. You can use +\Q...\E inside a character class. +</P> +<br><a name="SEC8" href="#TOC1">QUANTIFIERS</a><br> +<P> +<pre> + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy +</PRE> +</P> +<br><a name="SEC9" href="#TOC1">ANCHORS AND SIMPLE ASSERTIONS</a><br> +<P> +<pre> + \b word boundary (only ASCII letters recognized) + \B not a word boundary + ^ start of subject + also after internal newline in multiline mode + \A start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \Z end of subject + also before newline at end of subject + \z end of subject + \G first matching position in subject +</PRE> +</P> +<br><a name="SEC10" href="#TOC1">MATCH POINT RESET</a><br> +<P> +<pre> + \K reset start of match +</PRE> +</P> +<br><a name="SEC11" href="#TOC1">ALTERNATION</a><br> +<P> +<pre> + expr|expr|expr... +</PRE> +</P> +<br><a name="SEC12" href="#TOC1">CAPTURING</a><br> +<P> +<pre> + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative +</PRE> +</P> +<br><a name="SEC13" href="#TOC1">ATOMIC GROUPS</a><br> +<P> +<pre> + (?>...) atomic, non-capturing group +</PRE> +</P> +<br><a name="SEC14" href="#TOC1">COMMENT</a><br> +<P> +<pre> + (?#....) comment (not nestable) +</PRE> +</P> +<br><a name="SEC15" href="#TOC1">OPTION SETTING</a><br> +<P> +<pre> + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) +</pre> +The following is recognized only at the start of a pattern or after one of the +newline-setting options with similar syntax: +<pre> + (*UTF8) set UTF-8 mode +</PRE> +</P> +<br><a name="SEC16" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br> +<P> +<pre> + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind +</pre> +Each top-level branch of a look behind must be of a fixed length. +</P> +<br><a name="SEC17" href="#TOC1">BACKREFERENCES</a><br> +<P> +<pre> + \n reference by number (can be ambiguous) + \gn reference by number + \g{n} reference by number + \g{-n} relative reference by number + \k<name> reference by name (Perl) + \k'name' reference by name (Perl) + \g{name} reference by name (Perl) + \k{name} reference by name (.NET) + (?P=name) reference by name (Python) +</PRE> +</P> +<br><a name="SEC18" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br> +<P> +<pre> + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \g<name> call subpattern by name (Oniguruma) + \g'name' call subpattern by name (Oniguruma) + \g<n> call subpattern by absolute number (Oniguruma) + \g'n' call subpattern by absolute number (Oniguruma) + \g<+n> call subpattern by relative number (PCRE extension) + \g'+n' call subpattern by relative number (PCRE extension) + \g<-n> call subpattern by relative number (PCRE extension) + \g'-n' call subpattern by relative number (PCRE extension) +</PRE> +</P> +<br><a name="SEC19" href="#TOC1">CONDITIONAL PATTERNS</a><br> +<P> +<pre> + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition +</PRE> +</P> +<br><a name="SEC20" href="#TOC1">BACKTRACKING CONTROL</a><br> +<P> +The following act immediately they are reached: +<pre> + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) +</pre> +The following act only when a subsequent match failure causes a backtrack to +reach them. They all force a match failure, but they differ in what happens +afterwards. Those that advance the start-of-match point do so only if the +pattern is not anchored. +<pre> + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*SKIP) advance start to current matching position + (*THEN) local failure, backtrack to next alternation +</PRE> +</P> +<br><a name="SEC21" href="#TOC1">NEWLINE CONVENTIONS</a><br> +<P> +These are recognized only at the very start of the pattern or after a +(*BSR_...) or (*UTF8) option. +<pre> + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC22" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +These are recognized only at the very start of the pattern or after a +(*...) option that sets the newline convention or UTF-8 mode. +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC23" href="#TOC1">CALLOUTS</a><br> +<P> +<pre> + (?C) callout + (?Cn) callout with data n +</PRE> +</P> +<br><a name="SEC24" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcrepattern</b>(3), <b>pcreapi</b>(3), <b>pcrecallout</b>(3), +<b>pcrematching</b>(3), <b>pcre</b>(3). +</P> +<br><a name="SEC25" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC26" href="#TOC1">REVISION</a><br> +<P> +Last updated: 11 April 2009 +<br> +Copyright © 1997-2009 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> Modified: freeswitch/trunk/libs/pcre/doc/html/pcretest.html ============================================================================== --- freeswitch/trunk/libs/pcre/doc/html/pcretest.html (original) +++ freeswitch/trunk/libs/pcre/doc/html/pcretest.html Mon Jun 8 18:51:30 2009 @@ -23,8 +23,11 @@ <li><a name="TOC8" href="#SEC8">OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION</a> <li><a name="TOC9" href="#SEC9">RESTARTING AFTER A PARTIAL MATCH</a> <li><a name="TOC10" href="#SEC10">CALLOUTS</a> -<li><a name="TOC11" href="#SEC11">SAVING AND RELOADING COMPILED PATTERNS</a> -<li><a name="TOC12" href="#SEC12">AUTHOR</a> +<li><a name="TOC11" href="#SEC11">NON-PRINTING CHARACTERS</a> +<li><a name="TOC12" href="#SEC12">SAVING AND RELOADING COMPILED PATTERNS</a> +<li><a name="TOC13" href="#SEC13">SEE ALSO</a> +<li><a name="TOC14" href="#SEC14">AUTHOR</a> +<li><a name="TOC15" href="#SEC15">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> <P> @@ -43,6 +46,11 @@ </P> <br><a name="SEC2" href="#TOC1">OPTIONS</a><br> <P> +<b>-b</b> +Behave as if each regex has the <b>/B</b> (show bytecode) modifier; the internal +form is output after compilation. +</P> +<P> <b>-C</b> Output the version number of the PCRE library, and all available information about the optional features that are included, and then exit. @@ -50,7 +58,8 @@ <P> <b>-d</b> Behave as if each regex has the <b>/D</b> (debug) modifier; the internal -form is output after compilation. +form and information about the compiled pattern is output after compilation; +<b>-d</b> is equivalent to <b>-b -i</b>. </P> <P> <b>-dfa</b> @@ -59,11 +68,21 @@ standard <b>pcre_exec()</b> function (more detail is given below). </P> <P> +<b>-help</b> +Output a brief summary these options and then exit. +</P> +<P> <b>-i</b> Behave as if each regex has the <b>/I</b> modifier; information about the compiled pattern is given after compilation. </P> <P> +<b>-M</b> +Behave as if each data line contains the \M escape sequence; this causes +PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by +calling <b>pcre_exec()</b> repeatedly with different limits. +</P> +<P> <b>-m</b> Output the size of each compiled pattern after it has been compiled. This is equivalent to adding <b>/M</b> to each regular expression. For compatibility @@ -72,9 +91,11 @@ <P> <b>-o</b> <i>osize</i> Set the number of elements in the output vector that is used when calling -<b>pcre_exec()</b> to be <i>osize</i>. The default value is 45, which is enough -for 14 capturing subexpressions. The vector size can be changed for individual -matching calls by including \O in the data line (see below). +<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> to be <i>osize</i>. The default value +is 45, which is enough for 14 capturing subexpressions for <b>pcre_exec()</b> or +22 different matches for <b>pcre_dfa_exec()</b>. The vector size can be +changed for individual matching calls by including \O in the data line (see +below). </P> <P> <b>-p</b> @@ -96,7 +117,15 @@ Run each compile, study, and match many times with a timer, and output resulting time per compile or match (in milliseconds). Do not set <b>-m</b> with <b>-t</b>, because you will then get the size output a zillion times, and the -timing will be distorted. +timing will be distorted. You can control the number of iterations that are +used for timing by following <b>-t</b> with a number (as a separate item on the +command line). For example, "-t 1000" would iterate 1000 times. The default is +to iterate 500000 times. +</P> +<P> +<b>-tm</b> +This is like <b>-t</b> except that it times only the matching phase, not the +compile or study phases. </P> <br><a name="SEC3" href="#TOC1">DESCRIPTION</a><br> <P> @@ -107,6 +136,13 @@ expressions, and "data>" to prompt for data lines. </P> <P> +When <b>pcretest</b> is built, a configuration option can specify that it should +be linked with the <b>libreadline</b> library. When this is done, if the input +is from a terminal, it is read using the <b>readline()</b> function. This +provides line-editing and history facilities. The output from the <b>-help</b> +option states whether or not <b>readline()</b> will be used. +</P> +<P> The program handles any number of sets of input on a single input file. Each set starts with a regular expression, and continues with any number of data lines to be matched against the pattern. @@ -114,8 +150,8 @@ <P> Each data line is matched separately and independently. If you want to do multi-line matches, you have to use the \n escape sequence (or \r or \r\n, -depending on the newline setting) in a single line of input to encode the -newline characters. There is no limit on the length of data lines; the input +etc., depending on the newline setting) in a single line of input to encode the +newline sequences. There is no limit on the length of data lines; the input buffer is automatically extended if it is too small. </P> <P> @@ -168,20 +204,30 @@ The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: <pre> - <b>/A</b> PCRE_ANCHORED - <b>/C</b> PCRE_AUTO_CALLOUT - <b>/E</b> PCRE_DOLLAR_ENDONLY - <b>/f</b> PCRE_FIRSTLINE - <b>/J</b> PCRE_DUPNAMES - <b>/N</b> PCRE_NO_AUTO_CAPTURE - <b>/U</b> PCRE_UNGREEDY - <b>/X</b> PCRE_EXTRA - <b>/<cr></b> PCRE_NEWLINE_CR - <b>/<lf></b> PCRE_NEWLINE_LF - <b>/<crlf></b> PCRE_NEWLINE_CRLF + <b>/A</b> PCRE_ANCHORED + <b>/C</b> PCRE_AUTO_CALLOUT + <b>/E</b> PCRE_DOLLAR_ENDONLY + <b>/f</b> PCRE_FIRSTLINE + <b>/J</b> PCRE_DUPNAMES + <b>/N</b> PCRE_NO_AUTO_CAPTURE + <b>/U</b> PCRE_UNGREEDY + <b>/X</b> PCRE_EXTRA + <b>/<JS></b> PCRE_JAVASCRIPT_COMPAT + <b>/<cr></b> PCRE_NEWLINE_CR + <b>/<lf></b> PCRE_NEWLINE_LF + <b>/<crlf></b> PCRE_NEWLINE_CRLF + <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF + <b>/<any></b> PCRE_NEWLINE_ANY + <b>/<bsr_anycrlf></b> PCRE_BSR_ANYCRLF + <b>/<bsr_unicode></b> PCRE_BSR_UNICODE +</pre> +Those specifying line ending sequences are literal strings as shown, but the +letters can be in either case. This example sets multiline matching with CRLF +as the line ending sequence: +<pre> + /^abc/m<crlf> </pre> -Those specifying line endings are literal strings as shown. Details of the -meanings of these PCRE options are given in the +Details of the meanings of these PCRE options are given in the <a href="pcreapi.html"><b>pcreapi</b></a> documentation. </P> @@ -220,6 +266,14 @@ multiple copies of the same substring. </P> <P> +The <b>/B</b> modifier is a debugging feature. It requests that <b>pcretest</b> +output a representation of the compiled byte code after compilation. Normally +this information contains length and offset values; however, if <b>/Z</b> is +also present, this data is replaced by spaces. This is a special feature for +use in the automatic test scripts; it ensures that the same output is generated +for different internal link sizes. +</P> +<P> The <b>/L</b> modifier must be followed directly by the name of a locale, for example, <pre> @@ -238,10 +292,8 @@ pattern. If the pattern is studied, the results of that are also output. </P> <P> -The <b>/D</b> modifier is a PCRE debugging feature, which also assumes <b>/I</b>. -It causes the internal form of compiled regular expressions to be output after -compilation. If the pattern was studied, the information returned is also -output. +The <b>/D</b> modifier is a PCRE debugging feature, and is equivalent to +<b>/BI</b>, that is, both the <b>/B</b> and the <b>/I</b> modifiers. </P> <P> The <b>/F</b> modifier causes <b>pcretest</b> to flip the byte order of the @@ -289,15 +341,15 @@ expressions, you probably don't need any of these. The following escapes are recognized: <pre> - \a alarm (= BEL) - \b backspace - \e escape - \f formfeed - \n newline + \a alarm (BEL, \x07) + \b backspace (\x08) + \e escape (\x27) + \f formfeed (\x0c) + \n newline (\x0a) \qdd set the PCRE_MATCH_LIMIT limit to dd (any number of digits) - \r carriage return - \t tab - \v vertical tab + \r carriage return (\x0d) + \t tab (\x09) + \v vertical tab (\x0b) \nnn octal character (up to 3 octal digits) \xhh hexadecimal character (up to 2 hex digits) \x{hh...} hexadecimal character, any number of digits in UTF-8 mode @@ -331,11 +383,17 @@ \<cr> pass the PCRE_NEWLINE_CR option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> \<lf> pass the PCRE_NEWLINE_LF option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> \<crlf> pass the PCRE_NEWLINE_CRLF option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> + \<any> pass the PCRE_NEWLINE_ANY option to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> </pre> -The escapes that specify line endings are literal strings, exactly as shown. -A backslash followed by anything else just escapes the anything else. If the -very last character is a backslash, it is ignored. This gives a way of passing -an empty line as data, since a real empty line terminates the data input. +The escapes that specify line ending sequences are literal strings, exactly as +shown. No more than one newline setting should be present in any data line. +</P> +<P> +A backslash followed by anything else just escapes the anything else. If +the very last character is a backslash, it is ignored. This gives a way of +passing an empty line as data, since a real empty line terminates the data +input. </P> <P> If \M is present, <b>pcretest</b> calls <b>pcre_exec()</b> several times, with @@ -365,7 +423,10 @@ The use of \x{hh...} to represent UTF-8 characters is not dependent on the use of the <b>/8</b> modifier on the pattern. It is recognized always. There may be any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the UTF-8 rules. +six bytes, encoded according to the original UTF-8 rules of RFC 2279. This +allows for values in the range 0 to 0x7FFFFFFF. Note that not all of those are +valid Unicode code points, or indeed valid UTF-8 characters according to the +later rules in RFC 3629. </P> <br><a name="SEC6" href="#TOC1">THE ALTERNATIVE MATCHING FUNCTION</a><br> <P> @@ -398,7 +459,7 @@ of an interactive <b>pcretest</b> run. <pre> $ pcretest - PCRE version 5.00 07-Sep-2004 + PCRE version 7.0 30-Nov-2006 re> /^abc(\d+)/ data> abc123 @@ -407,11 +468,26 @@ data> xyz No match </pre> +Note that unset capturing substrings that are not followed by one that is set +are not returned by <b>pcre_exec()</b>, and are not shown by <b>pcretest</b>. In +the following example, there are two capturing substrings, but when the first +data line is matched, the second, unset substring is not shown. An "internal" +unset substring is shown as "<unset>", as for the second data line. +<pre> + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b +</pre> If the strings contain any non-printing characters, they are output as \0x escapes, or as \x{...} escapes if the <b>/8</b> modifier was present on the -pattern. If the pattern has the <b>/+</b> modifier, the output for substring 0 -is followed by the the rest of the subject string, identified by "0+" like -this: +pattern. See below for the definition of non-printing characters. If the +pattern has the <b>/+</b> modifier, the output for substring 0 is followed by +the the rest of the subject string, identified by "0+" like this: <pre> re> /cat/+ data> cataract @@ -441,10 +517,10 @@ parentheses after each string for <b>\C</b> and <b>\G</b>. </P> <P> -Note that while patterns can be continued over several lines (a plain ">" +Note that whereas patterns can be continued over several lines (a plain ">" prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \n escape (or \r or \r\n for those newline -settings). +included in data by means of the \n escape (or \r, \r\n, etc., depending on +the newline sequence setting). </P> <br><a name="SEC8" href="#TOC1">OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION</a><br> <P> @@ -463,7 +539,7 @@ longest matching string is always given first (and numbered zero). </P> <P> -If \fB/g\P is present on the pattern, the search for further matches resumes +If <b>/g</b> is present on the pattern, the search for further matches resumes at the end of the longest match. For example: <pre> re> /(tang|tangerine|tan)/g @@ -537,7 +613,19 @@ <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. </P> -<br><a name="SEC11" href="#TOC1">SAVING AND RELOADING COMPILED PATTERNS</a><br> +<br><a name="SEC11" href="#TOC1">NON-PRINTING CHARACTERS</a><br> +<P> +When <b>pcretest</b> is outputting text in the compiled version of a pattern, +bytes other than 32-126 are always treated as non-printing characters are are +therefore shown as hex escapes. +</P> +<P> +When <b>pcretest</b> is outputting text that is a matched part of a subject +string, it behaves in the same way, unless a different locale has been set for +the pattern (using the <b>/L</b> modifier). In this case, the <b>isprint()</b> +function to distinguish printing and non-printing characters. +</P> +<br><a name="SEC12" href="#TOC1">SAVING AND RELOADING COMPILED PATTERNS</a><br> <P> The facilities described in this section are not available when the POSIX inteface to PCRE is being used, that is, when the <b>/P</b> pattern modifier is @@ -599,18 +687,26 @@ Finally, if you attempt to load a file that is not in the correct format, the result is undefined. </P> -<br><a name="SEC12" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC13" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcre</b>(3), <b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3), +<b>pcrepartial</b>(d), <b>pcrepattern</b>(3), <b>pcreprecompile</b>(3). +</P> +<br><a name="SEC14" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> -University Computing Service, +University Computing Service +<br> +Cambridge CB2 3QH, England. <br> -Cambridge CB2 3QG, England. </P> +<br><a name="SEC15" href="#TOC1">REVISION</a><br> <P> -Last updated: 29 June 2006 +Last updated: 10 March 2009 +<br> +Copyright © 1997-2009 University of Cambridge. <br> -Copyright © 1997-2006 University of Cambridge. <p> Return to the <a href="index.html">PCRE index page</a>. </p> Added: freeswitch/trunk/libs/pcre/doc/index.html.src ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/index.html.src Mon Jun 8 18:51:30 2009 @@ -0,0 +1,140 @@ +<html> +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are + created by the 132html script. +--> +<head> +<title>PCRE specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>Perl-compatible Regular Expressions (PCRE)</h1> +<p> +The HTML documentation for PCRE comprises the following pages: +</p> + +<table> +<tr><td><a href="pcre.html">pcre</a></td> + <td>  Introductory page</td></tr> + +<tr><td><a href="pcre-config.html">pcre-config</a></td> + <td>  Information about the installation configuration</td></tr> + +<tr><td><a href="pcreapi.html">pcreapi</a></td> + <td>  PCRE's native API</td></tr> + +<tr><td><a href="pcrebuild.html">pcrebuild</a></td> + <td>  Options for building PCRE</td></tr> + +<tr><td><a href="pcrecallout.html">pcrecallout</a></td> + <td>  The <i>callout</i> facility</td></tr> + +<tr><td><a href="pcrecompat.html">pcrecompat</a></td> + <td>  Compability with Perl</td></tr> + +<tr><td><a href="pcrecpp.html">pcrecpp</a></td> + <td>  The C++ wrapper for the PCRE library</td></tr> + +<tr><td><a href="pcregrep.html">pcregrep</a></td> + <td>  The <b>pcregrep</b> command</td></tr> + +<tr><td><a href="pcrematching.html">pcrematching</a></td> + <td>  Discussion of the two matching algorithms</td></tr> + +<tr><td><a href="pcrepartial.html">pcrepartial</a></td> + <td>  Using PCRE for partial matching</td></tr> + +<tr><td><a href="pcrepattern.html">pcrepattern</a></td> + <td>  Specification of the regular expressions supported by PCRE</td></tr> + +<tr><td><a href="pcreperform.html">pcreperform</a></td> + <td>  Some comments on performance</td></tr> + +<tr><td><a href="pcreposix.html">pcreposix</a></td> + <td>  The POSIX API to the PCRE library</td></tr> + +<tr><td><a href="pcreprecompile.html">pcreprecompile</a></td> + <td>  How to save and re-use compiled patterns</td></tr> + +<tr><td><a href="pcresample.html">pcresample</a></td> + <td>  Description of the sample program</td></tr> + +<tr><td><a href="pcrestack.html">pcrestack</a></td> + <td>  Discussion of PCRE's stack usage</td></tr> + +<tr><td><a href="pcresyntax.html">pcresyntax</a></td> + <td>  Syntax quick-reference summary</td></tr> + +<tr><td><a href="pcretest.html">pcretest</a></td> + <td>  The <b>pcretest</b> command for testing PCRE</td></tr> +</table> + +<p> +There are also individual pages that summarize the interface for each function +in the library: +</p> + +<table> + +<tr><td><a href="pcre_compile.html">pcre_compile</a></td> + <td>  Compile a regular expression</td></tr> + +<tr><td><a href="pcre_compile2.html">pcre_compile2</a></td> + <td>  Compile a regular expression (alternate interface)</td></tr> + +<tr><td><a href="pcre_config.html">pcre_config</a></td> + <td>  Show build-time configuration options</td></tr> + +<tr><td><a href="pcre_copy_named_substring.html">pcre_copy_named_substring</a></td> + <td>  Extract named substring into given buffer</td></tr> + +<tr><td><a href="pcre_copy_substring.html">pcre_copy_substring</a></td> + <td>  Extract numbered substring into given buffer</td></tr> + +<tr><td><a href="pcre_dfa_exec.html">pcre_dfa_exec</a></td> + <td>  Match a compiled pattern to a subject string + (DFA algorithm; <i>not</i> Perl compatible)</td></tr> + +<tr><td><a href="pcre_exec.html">pcre_exec</a></td> + <td>  Match a compiled pattern to a subject string + (Perl compatible)</td></tr> + +<tr><td><a href="pcre_free_substring.html">pcre_free_substring</a></td> + <td>  Free extracted substring</td></tr> + +<tr><td><a href="pcre_free_substring_list.html">pcre_free_substring_list</a></td> + <td>  Free list of extracted substrings</td></tr> + +<tr><td><a href="pcre_fullinfo.html">pcre_fullinfo</a></td> + <td>  Extract information about a pattern</td></tr> + +<tr><td><a href="pcre_get_named_substring.html">pcre_get_named_substring</a></td> + <td>  Extract named substring into new memory</td></tr> + +<tr><td><a href="pcre_get_stringnumber.html">pcre_get_stringnumber</a></td> + <td>  Convert captured string name to number</td></tr> + +<tr><td><a href="pcre_get_substring.html">pcre_get_substring</a></td> + <td>  Extract numbered substring into new memory</td></tr> + +<tr><td><a href="pcre_get_substring_list.html">pcre_get_substring_list</a></td> + <td>  Extract all substrings into new memory</td></tr> + +<tr><td><a href="pcre_info.html">pcre_info</a></td> + <td>  Obsolete information extraction function</td></tr> + +<tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> + <td>  Build character tables in current locale</td></tr> + +<tr><td><a href="pcre_refcount.html">pcre_refcount</a></td> + <td>  Maintain reference count in compiled pattern</td></tr> + +<tr><td><a href="pcre_study.html">pcre_study</a></td> + <td>  Study a compiled pattern</td></tr> + +<tr><td><a href="pcre_version.html">pcre_version</a></td> + <td>  Return PCRE version and release date</td></tr> +</table> + +</html> Added: freeswitch/trunk/libs/pcre/doc/pcre-config.1 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/pcre-config.1 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,73 @@ +.TH PCRE-CONFIG 1 +.SH NAME +pcre-config - program to return PCRE configuration +.SH SYNOPSIS +.rs +.sp +.B pcre-config [--prefix] [--exec-prefix] [--version] [--libs] +.ti +5n +.B [--libs-posix] [--cflags] [--cflags-posix] +. +. +.SH DESCRIPTION +.rs +.sp +\fBpcre-config\fP returns the configuration of the installed PCRE +libraries and the options required to compile a program to use them. +. +. +.SH OPTIONS +.rs +.TP 10 +\fB--prefix\fP +Writes the directory prefix used in the PCRE installation for architecture +independent files (\fI/usr\fP on many systems, \fI/usr/local\fP on some +systems) to the standard output. +.TP 10 +\fB--exec-prefix\fP +Writes the directory prefix used in the PCRE installation for architecture +dependent files (normally the same as \fB--prefix\fP) to the standard output. +.TP 10 +\fB--version\fP +Writes the version number of the installed PCRE libraries to the standard +output. +.TP 10 +\fB--libs\fP +Writes to the standard output the command line options required to link +with PCRE (\fB-lpcre\fP on many systems). +.TP 10 +\fB--libs-posix\fP +Writes to the standard output the command line options required to link with +the PCRE posix emulation library (\fB-lpcreposix\fP \fB-lpcre\fP on many +systems). +.TP 10 +\fB--cflags\fP +Writes to the standard output the command line options required to compile +files that use PCRE (this may include some \fB-I\fP options, but is blank on +many systems). +.TP 10 +\fB--cflags-posix\fP +Writes to the standard output the command line options required to compile +files that use the PCRE posix emulation library (this may include some \fB-I\fP +options, but is blank on many systems). +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcre(3)\fP +. +. +.SH AUTHOR +.rs +.sp +This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been slightly revised as a generic PCRE man page. +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 18 April 2007 +.fi Added: freeswitch/trunk/libs/pcre/doc/pcre-config.txt ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/pcre-config.txt Mon Jun 8 18:51:30 2009 @@ -0,0 +1,67 @@ +PCRE-CONFIG(1) PCRE-CONFIG(1) + + + +NAME + pcre-config - program to return PCRE configuration + +SYNOPSIS + + pcre-config [--prefix] [--exec-prefix] [--version] [--libs] + [--libs-posix] [--cflags] [--cflags-posix] + + +DESCRIPTION + + pcre-config returns the configuration of the installed PCRE libraries + and the options required to compile a program to use them. + + +OPTIONS + + --prefix Writes the directory prefix used in the PCRE installation for + architecture independent files (/usr on many systems, + /usr/local on some systems) to the standard output. + + --exec-prefix + Writes the directory prefix used in the PCRE installation for + architecture dependent files (normally the same as --prefix) + to the standard output. + + --version Writes the version number of the installed PCRE libraries to + the standard output. + + --libs Writes to the standard output the command line options + required to link with PCRE (-lpcre on many systems). + + --libs-posix + Writes to the standard output the command line options + required to link with the PCRE posix emulation library + (-lpcreposix -lpcre on many systems). + + --cflags Writes to the standard output the command line options + required to compile files that use PCRE (this may include + some -I options, but is blank on many systems). + + --cflags-posix + Writes to the standard output the command line options + required to compile files that use the PCRE posix emulation + library (this may include some -I options, but is blank on + many systems). + + +SEE ALSO + + pcre(3) + + +AUTHOR + + This manual page was originally written by Mark Baker for the Debian + GNU/Linux system. It has been slightly revised as a generic PCRE man + page. + + +REVISION + + Last updated: 18 April 2007 Modified: freeswitch/trunk/libs/pcre/doc/pcre.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre.3 Mon Jun 8 18:51:30 2009 @@ -6,12 +6,18 @@ .sp The PCRE library is a set of functions that implement regular expression pattern matching using the same syntax and semantics as Perl, with just a few -differences. The current implementation of PCRE (release 6.x) corresponds -approximately with Perl 5.8, including support for UTF-8 encoded strings and -Unicode general category properties. However, this support has to be explicitly -enabled; it is not the default. +differences. Certain features that appeared in Python and PCRE before they +appeared in Perl are also available using the Python syntax. There is also some +support for certain .NET and Oniguruma syntax items, and there is an option for +requesting some minor changes that give better JavaScript compatibility. +.P +The current implementation of PCRE (release 7.x) corresponds approximately with +Perl 5.10, including support for UTF-8 encoded strings and Unicode general +category properties. However, UTF-8 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 5.1. .P -In addition to the Perl-compatible matching function, PCRE also contains an +In addition to the Perl-compatible matching function, PCRE contains an alternative matching function that matches the same compiled patterns in a different way. In certain circumstances, the alternative function has some advantages. For a discussion of the two matching algorithms, see the @@ -43,7 +49,11 @@ .\" HREF \fBpcrecompat\fR .\" -pages. +pages. There is a syntax summary in the +.\" HREF +\fBpcresyntax\fR +.\" +page. .P Some features of PCRE can be included, excluded, or changed when the library is built. The @@ -77,6 +87,7 @@ follows: .sp pcre this document + pcre-config show PCRE installation configuration information pcreapi details of PCRE's native C API pcrebuild options for building PCRE pcrecallout details of the callout feature @@ -88,6 +99,7 @@ .\" JOIN pcrepattern syntax and semantics of supported regular expressions + pcresyntax quick syntax reference pcreperform discussion of performance issues pcreposix the POSIX-compatible C API pcreprecompile details of saving and re-using precompiled patterns @@ -114,18 +126,15 @@ \fBpcrebuild\fP .\" documentation for details). In these cases the limit is substantially larger. -However, the speed of execution will be slower. +However, the speed of execution is slower. .P -All values in repeating quantifiers must be less than 65536. The maximum -compiled length of subpattern with an explicit repeat count is 30000 bytes. The -maximum number of capturing subpatterns is 65535. -.P -There is no limit to the number of non-capturing subpatterns, but the maximum -depth of nesting of all kinds of parenthesized subpattern, including capturing -subpatterns, assertions, and other types of subpattern, is 200. +All values in repeating quantifiers must be less than 65536. .P -The maximum length of name for a named subpattern is 32, and the maximum number -of named subpatterns is 10000. +There is no limit to the number of parenthesized subpatterns, but there can be +no more than 65535 capturing subpatterns. +.P +The maximum length of name for a named subpattern is 32 characters, and the +maximum number of named subpatterns is 10000. .P The maximum length of a subject string is the largest positive number that an integer variable can hold. However, when using the traditional matching @@ -137,7 +146,7 @@ \fBpcrestack\fP .\" documentation. -.sp +. .\" HTML <a name="utf8support"></a> . . @@ -154,13 +163,14 @@ .\" HREF \fBpcre_compile()\fP .\" -with the PCRE_UTF8 option flag. When you do this, both the pattern and any -subject strings that are matched against it are treated as UTF-8 strings -instead of just strings of bytes. +with the PCRE_UTF8 option flag, or the pattern must start with the sequence +(*UTF8). When either of these is the case, both the pattern and any subject +strings that are matched against it are treated as UTF-8 strings instead of +just strings of bytes. .P If you compile PCRE with UTF-8 support, but do not use it at run time, the library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag in several places, so should not be very large. +to testing the PCRE_UTF8 flag occasionally, so should not be very big. .P If PCRE is built with Unicode character property support (which implies UTF-8 support), the escape sequences \ep{..}, \eP{..}, and \eX are supported. @@ -175,46 +185,83 @@ \ep{L} matches a letter. Its Perl synonym, \ep{Letter}, is not supported. Furthermore, in Perl, many properties may optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE does not support this. -.P -The following comments apply when PCRE is running in UTF-8 mode: -.P -1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are checked for validity on entry to the relevant functions. If an invalid -UTF-8 string is passed, an error return is given. In some situations, you may -already know that your strings are valid, and therefore want to skip these -checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag -at compile time or at run time, PCRE assumes that the pattern or subject it -is given (respectively) contains only valid UTF-8 codes. In this case, it does -not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to -PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program -may crash. -.P -2. An unbraced hexadecimal escape sequence (such as \exb3) matches a two-byte +. +.\" HTML <a name="utf8strings"></a> +. +.SS "Validity of UTF-8 strings" +.rs +.sp +When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects +are (by default) checked for validity on entry to the relevant functions. From +release 7.3 of PCRE, the check is according the rules of RFC 3629, which are +themselves derived from the Unicode specification. Earlier releases of PCRE +followed the rules of RFC 2279, which allows the full range of 31-bit values (0 +to 0x7FFFFFFF). The current check allows only values in the range U+0 to +U+10FFFF, excluding U+D800 to U+DFFF. +.P +The excluded code points are the "Low Surrogate Area" of Unicode, of which the +Unicode Standard says this: "The Low Surrogate Area does not contain any +character assignments, consequently no character code charts or namelists are +provided for this area. Surrogates are reserved for use with UTF-16 and then +must be used in pairs." The code points that are encoded by UTF-16 pairs are +available as independent code points in the UTF-8 encoding. (In other words, +the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up +UTF-8.) +.P +If an invalid UTF-8 string is passed to PCRE, an error return +(PCRE_ERROR_BADUTF8) is given. In some situations, you may already know that +your strings are valid, and therefore want to skip these checks in order to +improve performance. If you set the PCRE_NO_UTF8_CHECK flag at compile time or +at run time, PCRE assumes that the pattern or subject it is given +(respectively) contains only valid UTF-8 codes. In this case, it does not +diagnose an invalid UTF-8 string. +.P +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, what +happens depends on why the string is invalid. If the string conforms to the +"old" definition of UTF-8 (RFC 2279), it is processed as a string of characters +in the range 0 to 0x7FFFFFFF. In other words, apart from the initial validity +test, PCRE (when in UTF-8 mode) handles strings according to the more liberal +rules of RFC 2279. However, if the string does not even conform to RFC 2279, +the result is undefined. Your program may crash. +.P +If you want to process strings of values in the full range 0 to 0x7FFFFFFF, +encoded in a UTF-8-like manner as per the old RFC, you can set +PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in this +situation, you will have to apply your own validity check. +. +.SS "General comments about UTF-8 mode" +.rs +.sp +1. An unbraced hexadecimal escape sequence (such as \exb3) matches a two-byte UTF-8 character if the value is greater than 127. .P -3. Octal numbers up to \e777 are recognized, and match two-byte UTF-8 +2. Octal numbers up to \e777 are recognized, and match two-byte UTF-8 characters for values greater than \e177. .P -4. Repeat quantifiers apply to complete UTF-8 characters, not to individual +3. Repeat quantifiers apply to complete UTF-8 characters, not to individual bytes, for example: \ex{100}{3}. .P -5. The dot metacharacter matches one UTF-8 character instead of a single byte. +4. The dot metacharacter matches one UTF-8 character instead of a single byte. .P -6. The escape sequence \eC can be used to match a single byte in UTF-8 mode, +5. The escape sequence \eC can be used to match a single byte in UTF-8 mode, but its use can lead to some strange effects. This facility is not available in the alternative matching function, \fBpcre_dfa_exec()\fP. .P -7. The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly +6. The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly test characters of any code value, but the characters that PCRE recognizes as digits, spaces, or word characters remain the same set as before, all with values less than 256. This remains true even when PCRE includes Unicode property support, because to do otherwise would slow down PCRE in many common cases. If you really want to test for a wider sense of, say, "digit", you -must use Unicode property tests such as \ep{Nd}. +must use Unicode property tests such as \ep{Nd}. Note that this also applies to +\eb, because it is defined in terms of \ew and \eW. .P -8. Similarly, characters that match the POSIX named character classes are all +7. Similarly, characters that match the POSIX named character classes are all low-valued characters. .P +8. However, the Perl 5.10 horizontal and vertical whitespace matching escapes +(\eh, \eH, \ev, and \eV) do match all the appropriate Unicode characters. +.P 9. Case-insensitive matching applies only to characters whose values are less than 128, unless PCRE is built with Unicode property support. Even when Unicode property support is available, PCRE still uses its own character tables when @@ -225,20 +272,25 @@ letter's cases. There are a small number of many-to-one mappings in Unicode; these are not supported by PCRE. . +. .SH AUTHOR .rs .sp +.nf Philip Hazel -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. +University Computing Service +Cambridge CB2 3QH, England. +.fi .P Putting an actual email address here seems to have been a spam magnet, so I've -taken it away. If you want to email me, use my initial and surname, separated -by a dot, at the domain ucs.cam.ac.uk. +taken it away. If you want to email me, use my two initials, followed by the +two digits 10, at the domain cam.ac.uk. +. +. +.SH REVISION +.rs .sp -.in 0 -Last updated: 05 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +.nf +Last updated: 11 April 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcre.txt ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre.txt (original) +++ freeswitch/trunk/libs/pcre/doc/pcre.txt Mon Jun 8 18:51:30 2009 @@ -18,29 +18,37 @@ The PCRE library is a set of functions that implement regular expres- sion pattern matching using the same syntax and semantics as Perl, with - just a few differences. The current implementation of PCRE (release - 6.x) corresponds approximately with Perl 5.8, including support for - UTF-8 encoded strings and Unicode general category properties. However, - this support has to be explicitly enabled; it is not the default. - - In addition to the Perl-compatible matching function, PCRE also con- - tains an alternative matching function that matches the same compiled - patterns in a different way. In certain circumstances, the alternative - function has some advantages. For a discussion of the two matching - algorithms, see the pcrematching page. - - PCRE is written in C and released as a C library. A number of people - have written wrappers and interfaces of various kinds. In particular, - Google Inc. have provided a comprehensive C++ wrapper. This is now + just a few differences. Certain features that appeared in Python and + PCRE before they appeared in Perl are also available using the Python + syntax. There is also some support for certain .NET and Oniguruma syn- + tax items, and there is an option for requesting some minor changes + that give better JavaScript compatibility. + + The current implementation of PCRE (release 7.x) corresponds approxi- + mately with Perl 5.10, including support for UTF-8 encoded strings and + Unicode general category properties. However, UTF-8 and Unicode support + has to be explicitly enabled; it is not the default. The Unicode tables + correspond to Unicode release 5.1. + + In addition to the Perl-compatible matching function, PCRE contains an + alternative matching function that matches the same compiled patterns + in a different way. In certain circumstances, the alternative function + has some advantages. For a discussion of the two matching algorithms, + see the pcrematching page. + + PCRE is written in C and released as a C library. A number of people + have written wrappers and interfaces of various kinds. In particular, + Google Inc. have provided a comprehensive C++ wrapper. This is now included as part of the PCRE distribution. The pcrecpp page has details - of this interface. Other people's contributions can be found in the + of this interface. Other people's contributions can be found in the Contrib directory at the primary FTP site, which is: ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre - Details of exactly which Perl regular expression features are and are + Details of exactly which Perl regular expression features are and are not supported by PCRE are given in separate documents. See the pcrepat- - tern and pcrecompat pages. + tern and pcrecompat pages. There is a syntax summary in the pcresyntax + page. Some features of PCRE can be included, excluded, or changed when the library is built. The pcre_config() function makes it possible for a @@ -67,6 +75,7 @@ of searching. The sections are as follows: pcre this document + pcre-config show PCRE installation configuration information pcreapi details of PCRE's native C API pcrebuild options for building PCRE pcrecallout details of the callout feature @@ -77,6 +86,7 @@ pcrepartial details of the partial matching facility pcrepattern syntax and semantics of supported regular expressions + pcresyntax quick syntax reference pcreperform discussion of performance issues pcreposix the POSIX-compatible C API pcreprecompile details of saving and re-using precompiled patterns @@ -84,60 +94,57 @@ pcrestack discussion of stack usage pcretest description of the pcretest testing command - In addition, in the "man" and HTML formats, there is a short page for + In addition, in the "man" and HTML formats, there is a short page for each C library function, listing its arguments and results. LIMITATIONS - There are some size limitations in PCRE but it is hoped that they will + There are some size limitations in PCRE but it is hoped that they will never in practice be relevant. - The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE + The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is compiled with the default internal linkage size of 2. If you want to - process regular expressions that are truly enormous, you can compile - PCRE with an internal linkage size of 3 or 4 (see the README file in - the source distribution and the pcrebuild documentation for details). - In these cases the limit is substantially larger. However, the speed - of execution will be slower. - - All values in repeating quantifiers must be less than 65536. The maxi- - mum compiled length of subpattern with an explicit repeat count is - 30000 bytes. The maximum number of capturing subpatterns is 65535. - - There is no limit to the number of non-capturing subpatterns, but the - maximum depth of nesting of all kinds of parenthesized subpattern, - including capturing subpatterns, assertions, and other types of subpat- - tern, is 200. + process regular expressions that are truly enormous, you can compile + PCRE with an internal linkage size of 3 or 4 (see the README file in + the source distribution and the pcrebuild documentation for details). + In these cases the limit is substantially larger. However, the speed + of execution is slower. + + All values in repeating quantifiers must be less than 65536. + + There is no limit to the number of parenthesized subpatterns, but there + can be no more than 65535 capturing subpatterns. - The maximum length of name for a named subpattern is 32, and the maxi- - mum number of named subpatterns is 10000. + The maximum length of name for a named subpattern is 32 characters, and + the maximum number of named subpatterns is 10000. - The maximum length of a subject string is the largest positive number - that an integer variable can hold. However, when using the traditional + The maximum length of a subject string is the largest positive number + that an integer variable can hold. However, when using the traditional matching function, PCRE uses recursion to handle subpatterns and indef- - inite repetition. This means that the available stack space may limit + inite repetition. This means that the available stack space may limit the size of a subject string that can be processed by certain patterns. For a discussion of stack issues, see the pcrestack documentation. UTF-8 AND UNICODE PROPERTY SUPPORT - From release 3.3, PCRE has had some support for character strings - encoded in the UTF-8 format. For release 4.0 this was greatly extended - to cover most common requirements, and in release 5.0 additional sup- + From release 3.3, PCRE has had some support for character strings + encoded in the UTF-8 format. For release 4.0 this was greatly extended + to cover most common requirements, and in release 5.0 additional sup- port for Unicode general category properties was added. - In order process UTF-8 strings, you must build PCRE to include UTF-8 - support in the code, and, in addition, you must call pcre_compile() - with the PCRE_UTF8 option flag. When you do this, both the pattern and - any subject strings that are matched against it are treated as UTF-8 - strings instead of just strings of bytes. + In order process UTF-8 strings, you must build PCRE to include UTF-8 + support in the code, and, in addition, you must call pcre_compile() + with the PCRE_UTF8 option flag, or the pattern must start with the + sequence (*UTF8). When either of these is the case, both the pattern + and any subject strings that are matched against it are treated as + UTF-8 strings instead of just strings of bytes. If you compile PCRE with UTF-8 support, but do not use it at run time, the library will be a bit bigger, but the additional run time overhead - is limited to testing the PCRE_UTF8 flag in several places, so should - not be very large. + is limited to testing the PCRE_UTF8 flag occasionally, so should not be + very big. If PCRE is built with Unicode character property support (which implies UTF-8 support), the escape sequences \p{..}, \P{..}, and \X are sup- @@ -151,72 +158,110 @@ optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE does not support this. - The following comments apply when PCRE is running in UTF-8 mode: + Validity of UTF-8 strings - 1. When you set the PCRE_UTF8 flag, the strings passed as patterns and - subjects are checked for validity on entry to the relevant functions. - If an invalid UTF-8 string is passed, an error return is given. In some - situations, you may already know that your strings are valid, and - therefore want to skip these checks in order to improve performance. If - you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, - PCRE assumes that the pattern or subject it is given (respectively) - contains only valid UTF-8 codes. In this case, it does not diagnose an - invalid UTF-8 string. If you pass an invalid UTF-8 string to PCRE when - PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program may - crash. + When you set the PCRE_UTF8 flag, the strings passed as patterns and + subjects are (by default) checked for validity on entry to the relevant + functions. From release 7.3 of PCRE, the check is according the rules + of RFC 3629, which are themselves derived from the Unicode specifica- + tion. Earlier releases of PCRE followed the rules of RFC 2279, which + allows the full range of 31-bit values (0 to 0x7FFFFFFF). The current + check allows only values in the range U+0 to U+10FFFF, excluding U+D800 + to U+DFFF. + + The excluded code points are the "Low Surrogate Area" of Unicode, of + which the Unicode Standard says this: "The Low Surrogate Area does not + contain any character assignments, consequently no character code + charts or namelists are provided for this area. Surrogates are reserved + for use with UTF-16 and then must be used in pairs." The code points + that are encoded by UTF-16 pairs are available as independent code + points in the UTF-8 encoding. (In other words, the whole surrogate + thing is a fudge for UTF-16 which unfortunately messes up UTF-8.) + + If an invalid UTF-8 string is passed to PCRE, an error return + (PCRE_ERROR_BADUTF8) is given. In some situations, you may already know + that your strings are valid, and therefore want to skip these checks in + order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag at + compile time or at run time, PCRE assumes that the pattern or subject + it is given (respectively) contains only valid UTF-8 codes. In this + case, it does not diagnose an invalid UTF-8 string. + + If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, + what happens depends on why the string is invalid. If the string con- + forms to the "old" definition of UTF-8 (RFC 2279), it is processed as a + string of characters in the range 0 to 0x7FFFFFFF. In other words, + apart from the initial validity test, PCRE (when in UTF-8 mode) handles + strings according to the more liberal rules of RFC 2279. However, if + the string does not even conform to RFC 2279, the result is undefined. + Your program may crash. + + If you want to process strings of values in the full range 0 to + 0x7FFFFFFF, encoded in a UTF-8-like manner as per the old RFC, you can + set PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in + this situation, you will have to apply your own validity check. - 2. An unbraced hexadecimal escape sequence (such as \xb3) matches a + General comments about UTF-8 mode + + 1. An unbraced hexadecimal escape sequence (such as \xb3) matches a two-byte UTF-8 character if the value is greater than 127. - 3. Octal numbers up to \777 are recognized, and match two-byte UTF-8 + 2. Octal numbers up to \777 are recognized, and match two-byte UTF-8 characters for values greater than \177. - 4. Repeat quantifiers apply to complete UTF-8 characters, not to indi- + 3. Repeat quantifiers apply to complete UTF-8 characters, not to indi- vidual bytes, for example: \x{100}{3}. - 5. The dot metacharacter matches one UTF-8 character instead of a sin- + 4. The dot metacharacter matches one UTF-8 character instead of a sin- gle byte. - 6. The escape sequence \C can be used to match a single byte in UTF-8 + 5. The escape sequence \C can be used to match a single byte in UTF-8 mode, but its use can lead to some strange effects. This facility is not available in the alternative matching function, pcre_dfa_exec(). - 7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly + 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test characters of any code value, but the characters that PCRE recog- nizes as digits, spaces, or word characters remain the same set as before, all with values less than 256. This remains true even when PCRE includes Unicode property support, because to do otherwise would slow down PCRE in many common cases. If you really want to test for a wider sense of, say, "digit", you must use Unicode property tests such as - \p{Nd}. + \p{Nd}. Note that this also applies to \b, because it is defined in + terms of \w and \W. - 8. Similarly, characters that match the POSIX named character classes + 7. Similarly, characters that match the POSIX named character classes are all low-valued characters. - 9. Case-insensitive matching applies only to characters whose values - are less than 128, unless PCRE is built with Unicode property support. - Even when Unicode property support is available, PCRE still uses its - own character tables when checking the case of low-valued characters, - so as not to degrade performance. The Unicode property information is + 8. However, the Perl 5.10 horizontal and vertical whitespace matching + escapes (\h, \H, \v, and \V) do match all the appropriate Unicode char- + acters. + + 9. Case-insensitive matching applies only to characters whose values + are less than 128, unless PCRE is built with Unicode property support. + Even when Unicode property support is available, PCRE still uses its + own character tables when checking the case of low-valued characters, + so as not to degrade performance. The Unicode property information is used only for characters with higher values. Even when Unicode property support is available, PCRE supports case-insensitive matching only when - there is a one-to-one mapping between a letter's cases. There are a - small number of many-to-one mappings in Unicode; these are not sup- + there is a one-to-one mapping between a letter's cases. There are a + small number of many-to-one mappings in Unicode; these are not sup- ported by PCRE. AUTHOR Philip Hazel - University Computing Service, - Cambridge CB2 3QG, England. + University Computing Service + Cambridge CB2 3QH, England. + + Putting an actual email address here seems to have been a spam magnet, + so I've taken it away. If you want to email me, use my two initials, + followed by the two digits 10, at the domain cam.ac.uk. - Putting an actual email address here seems to have been a spam magnet, - so I've taken it away. If you want to email me, use my initial and sur- - name, separated by a dot, at the domain ucs.cam.ac.uk. -Last updated: 05 June 2006 -Copyright (c) 1997-2006 University of Cambridge. +REVISION + + Last updated: 11 April 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -230,20 +275,25 @@ PCRE BUILD-TIME OPTIONS This document describes the optional features of PCRE that can be - selected when the library is compiled. They are all selected, or dese- - lected, by providing options to the configure script that is run before - the make command. The complete list of options for configure (which - includes the standard ones such as the selection of the installation - directory) can be obtained by running + selected when the library is compiled. It assumes use of the configure + script, where the optional features are selected or deselected by pro- + viding options to configure before running the make command. However, + the same options can be selected in both Unix-like and non-Unix-like + environments using the GUI facility of CMakeSetup if you are using + CMake instead of configure to build PCRE. + + The complete list of options for configure (which includes the standard + ones such as the selection of the installation directory) can be + obtained by running ./configure --help - The following sections describe certain options whose names begin with - --enable or --disable. These settings specify changes to the defaults - for the configure command. Because of the way that configure works, - --enable and --disable always come in pairs, so the complementary - option always exists as well, but as it specifies the default, it is - not described. + The following sections include descriptions of options whose names + begin with --enable or --disable. These settings specify changes to the + defaults for the configure command. Because of the way that configure + works, --enable and --disable always come in pairs, so the complemen- + tary option always exists as well, but as it specifies the default, it + is not described. C++ SUPPORT @@ -259,41 +309,46 @@ UTF-8 SUPPORT - To build PCRE with support for UTF-8 character strings, add + To build PCRE with support for UTF-8 Unicode character strings, add --enable-utf8 - to the configure command. Of itself, this does not make PCRE treat - strings as UTF-8. As well as compiling PCRE with this option, you also - have have to set the PCRE_UTF8 option when you call the pcre_compile() + to the configure command. Of itself, this does not make PCRE treat + strings as UTF-8. As well as compiling PCRE with this option, you also + have have to set the PCRE_UTF8 option when you call the pcre_compile() function. + If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE + expects its input to be either ASCII or UTF-8 (depending on the runtime + option). It is not possible to support both EBCDIC and UTF-8 codes in + the same version of the library. Consequently, --enable-utf8 and + --enable-ebcdic are mutually exclusive. + UNICODE CHARACTER PROPERTY SUPPORT - UTF-8 support allows PCRE to process character values greater than 255 - in the strings that it handles. On its own, however, it does not pro- + UTF-8 support allows PCRE to process character values greater than 255 + in the strings that it handles. On its own, however, it does not pro- vide any facilities for accessing the properties of such characters. If - you want to be able to use the pattern escapes \P, \p, and \X, which + you want to be able to use the pattern escapes \P, \p, and \X, which refer to Unicode character properties, you must add --enable-unicode-properties - to the configure command. This implies UTF-8 support, even if you have + to the configure command. This implies UTF-8 support, even if you have not explicitly requested it. - Including Unicode property support adds around 90K of tables to the - PCRE library, approximately doubling its size. Only the general cate- - gory properties such as Lu and Nd are supported. Details are given in - the pcrepattern documentation. + Including Unicode property support adds around 30K of tables to the + PCRE library. Only the general category properties such as Lu and Nd + are supported. Details are given in the pcrepattern documentation. CODE VALUE OF NEWLINE - By default, PCRE interprets character 10 (linefeed, LF) as indicating + By default, PCRE interprets the linefeed (LF) character as indicating the end of a line. This is the normal newline character on Unix-like - systems. You can compile PCRE to use character 13 (carriage return, CR) - instead, by adding + systems. You can compile PCRE to use carriage return (CR) instead, by + adding --enable-newline-is-cr @@ -305,10 +360,33 @@ --enable-newline-is-crlf - to the configure command. Whatever line ending convention is selected - when PCRE is built can be overridden when the library functions are - called. At build time it is conventional to use the standard for your - operating system. + to the configure command. There is a fourth option, specified by + + --enable-newline-is-anycrlf + + which causes PCRE to recognize any of the three sequences CR, LF, or + CRLF as indicating a line ending. Finally, a fifth option, specified by + + --enable-newline-is-any + + causes PCRE to recognize any Unicode newline sequence. + + Whatever line ending convention is selected when PCRE is built can be + overridden when the library functions are called. At build time it is + conventional to use the standard for your operating system. + + +WHAT \R MATCHES + + By default, the sequence \R in a pattern matches any Unicode newline + sequence, whatever has been selected as the line ending sequence. If + you specify + + --enable-bsr-anycrlf + + the default is changed so that \R matches only CR, LF, or CRLF. What- + ever is selected when PCRE is built can be overridden when the library + functions are called. BUILDING SHARED AND STATIC LIBRARIES @@ -356,81 +434,161 @@ longer offsets slows down the operation of PCRE because it has to load additional bytes when handling them. - If you build PCRE with an increased link size, test 2 (and test 5 if - you are using UTF-8) will fail. Part of the output of these tests is a - representation of the compiled pattern, and this changes with the link - size. - AVOIDING EXCESSIVE STACK USAGE When matching with the pcre_exec() function, PCRE implements backtrack- - ing by making recursive calls to an internal function called match(). - In environments where the size of the stack is limited, this can se- - verely limit PCRE's operation. (The Unix environment does not usually + ing by making recursive calls to an internal function called match(). + In environments where the size of the stack is limited, this can se- + verely limit PCRE's operation. (The Unix environment does not usually suffer from this problem, but it may sometimes be necessary to increase - the maximum stack size. There is a discussion in the pcrestack docu- - mentation.) An alternative approach to recursion that uses memory from - the heap to remember data, instead of using recursive function calls, - has been implemented to work round the problem of limited stack size. + the maximum stack size. There is a discussion in the pcrestack docu- + mentation.) An alternative approach to recursion that uses memory from + the heap to remember data, instead of using recursive function calls, + has been implemented to work round the problem of limited stack size. If you want to build a version of PCRE that works this way, add --disable-stack-for-recursion - to the configure command. With this configuration, PCRE will use the - pcre_stack_malloc and pcre_stack_free variables to call memory manage- - ment functions. Separate functions are provided because the usage is - very predictable: the block sizes requested are always the same, and - the blocks are always freed in reverse order. A calling program might - be able to implement optimized functions that perform better than the - standard malloc() and free() functions. PCRE runs noticeably more - slowly when built in this way. This option affects only the pcre_exec() - function; it is not relevant for the the pcre_dfa_exec() function. + to the configure command. With this configuration, PCRE will use the + pcre_stack_malloc and pcre_stack_free variables to call memory manage- + ment functions. By default these point to malloc() and free(), but you + can replace the pointers so that your own functions are used. + + Separate functions are provided rather than using pcre_malloc and + pcre_free because the usage is very predictable: the block sizes + requested are always the same, and the blocks are always freed in + reverse order. A calling program might be able to implement optimized + functions that perform better than malloc() and free(). PCRE runs + noticeably more slowly when built in this way. This option affects only + the pcre_exec() function; it is not relevant for the the + pcre_dfa_exec() function. LIMITING PCRE RESOURCE USAGE - Internally, PCRE has a function called match(), which it calls repeat- - edly (sometimes recursively) when matching a pattern with the - pcre_exec() function. By controlling the maximum number of times this - function may be called during a single matching operation, a limit can - be placed on the resources used by a single call to pcre_exec(). The - limit can be changed at run time, as described in the pcreapi documen- - tation. The default is 10 million, but this can be changed by adding a + Internally, PCRE has a function called match(), which it calls repeat- + edly (sometimes recursively) when matching a pattern with the + pcre_exec() function. By controlling the maximum number of times this + function may be called during a single matching operation, a limit can + be placed on the resources used by a single call to pcre_exec(). The + limit can be changed at run time, as described in the pcreapi documen- + tation. The default is 10 million, but this can be changed by adding a setting such as --with-match-limit=500000 - to the configure command. This setting has no effect on the + to the configure command. This setting has no effect on the pcre_dfa_exec() matching function. - In some environments it is desirable to limit the depth of recursive + In some environments it is desirable to limit the depth of recursive calls of match() more strictly than the total number of calls, in order - to restrict the maximum amount of stack (or heap, if --disable-stack- + to restrict the maximum amount of stack (or heap, if --disable-stack- for-recursion is specified) that is used. A second limit controls this; - it defaults to the value that is set for --with-match-limit, which - imposes no additional constraints. However, you can set a lower limit + it defaults to the value that is set for --with-match-limit, which + imposes no additional constraints. However, you can set a lower limit by adding, for example, --with-match-limit-recursion=10000 - to the configure command. This value can also be overridden at run + to the configure command. This value can also be overridden at run time. +CREATING CHARACTER TABLES AT BUILD TIME + + PCRE uses fixed tables for processing characters whose code values are + less than 256. By default, PCRE is built with a set of tables that are + distributed in the file pcre_chartables.c.dist. These tables are for + ASCII codes only. If you add + + --enable-rebuild-chartables + + to the configure command, the distributed tables are no longer used. + Instead, a program called dftables is compiled and run. This outputs + the source for new set of tables, created in the default locale of your + C runtime system. (This method of replacing the tables does not work if + you are cross compiling, because dftables is run on the local host. If + you need to create alternative tables when cross compiling, you will + have to do so "by hand".) + + USING EBCDIC CODE PCRE assumes by default that it will run in an environment where the character code is ASCII (or Unicode, which is a superset of ASCII). - PCRE can, however, be compiled to run in an EBCDIC environment by - adding + This is the case for most computer operating systems. PCRE can, how- + ever, be compiled to run in an EBCDIC environment by adding --enable-ebcdic - to the configure command. + to the configure command. This setting implies --enable-rebuild-charta- + bles. You should only use it if you know that you are in an EBCDIC + environment (for example, an IBM mainframe operating system). The + --enable-ebcdic option is incompatible with --enable-utf8. + + +PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + By default, pcregrep reads all files as plain text. You can build it so + that it recognizes files whose names end in .gz or .bz2, and reads them + with libz or libbz2, respectively, by adding one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + to the configure command. These options naturally require that the rel- + evant libraries are installed on your system. Configuration will fail + if they are not. + + +PCRETEST OPTION FOR LIBREADLINE SUPPORT + + If you add + + --enable-pcretest-libreadline + + to the configure command, pcretest is linked with the libreadline + library, and when its input is from a terminal, it reads it using the + readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + + Setting this option causes the -lreadline option to be added to the + pcretest build. In many operating environments with a sytem-installed + libreadline this is sufficient. However, in some environments (e.g. if + an unmodified distribution version of readline is in use), some extra + configuration may be necessary. The INSTALL file for libreadline says + this: + + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." + + If your environment has not been set up so that an appropriate library + is automatically included, you may need to add something like + + LIBS="-ncurses" + + immediately before the configure command. + + +SEE ALSO + + pcreapi(3), pcre_config(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 17 March 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -466,7 +624,7 @@ <something> <something else> <something further> there are three possible answers. The standard algorithm finds only one - of them, whereas the DFA algorithm finds all three. + of them, whereas the alternative algorithm finds all three. REGULAR EXPRESSIONS AS TREES @@ -482,8 +640,8 @@ THE STANDARD MATCHING ALGORITHM - In the terminology of Jeffrey Friedl's book Mastering Regular Expres- - sions, the standard algorithm is an "NFA algorithm". It conducts a + In the terminology of Jeffrey Friedl's book "Mastering Regular Expres- + sions", the standard algorithm is an "NFA algorithm". It conducts a depth-first search of the pattern tree. That is, it proceeds along a single path through the tree, checking that the subject matches what is required. When there is a mismatch, the algorithm tries any alterna- @@ -507,21 +665,22 @@ This provides support for capturing parentheses and back references. -THE DFA MATCHING ALGORITHM +THE ALTERNATIVE MATCHING ALGORITHM - DFA stands for "deterministic finite automaton", but you do not need to - understand the origins of that name. This algorithm conducts a breadth- - first search of the tree. Starting from the first matching point in the - subject, it scans the subject string from left to right, once, charac- - ter by character, and as it does this, it remembers all the paths - through the tree that represent valid matches. - - The scan continues until either the end of the subject is reached, or - there are no more unterminated paths. At this point, terminated paths - represent the different matching possibilities (if there are none, the - match has failed). Thus, if there is more than one possible match, + This algorithm conducts a breadth-first search of the tree. Starting + from the first matching point in the subject, it scans the subject + string from left to right, once, character by character, and as it does + this, it remembers all the paths through the tree that represent valid + matches. In Friedl's terminology, this is a kind of "DFA algorithm", + though it is not implemented as a traditional finite state machine (it + keeps multiple states active simultaneously). + + The scan continues until either the end of the subject is reached, or + there are no more unterminated paths. At this point, terminated paths + represent the different matching possibilities (if there are none, the + match has failed). Thus, if there is more than one possible match, this algorithm finds all of them, and in particular, it finds the long- - est. In PCRE, there is an option to stop the algorithm after the first + est. In PCRE, there is an option to stop the algorithm after the first match (which is necessarily the shortest) has been found. Note that all the matches that are found start at the same point in the @@ -529,42 +688,63 @@ cat(er(pillar)?) - is matched against the string "the caterpillar catchment", the result - will be the three strings "cat", "cater", and "caterpillar" that start + is matched against the string "the caterpillar catchment", the result + will be the three strings "cat", "cater", and "caterpillar" that start at the fourth character of the subject. The algorithm does not automat- ically move on to find matches that start at later positions. There are a number of features of PCRE regular expressions that are not - supported by the DFA matching algorithm. They are as follows: + supported by the alternative matching algorithm. They are as follows: - 1. Because the algorithm finds all possible matches, the greedy or - ungreedy nature of repetition quantifiers is not relevant. Greedy and - ungreedy quantifiers are treated in exactly the same way. + 1. Because the algorithm finds all possible matches, the greedy or + ungreedy nature of repetition quantifiers is not relevant. Greedy and + ungreedy quantifiers are treated in exactly the same way. However, pos- + sessive quantifiers can make a difference when what follows could also + match what is quantified, for example in a pattern like this: + + ^a++\w! + + This pattern matches "aaab!" but not "aaa!", which would be matched by + a non-possessive quantifier. Similarly, if an atomic group is present, + it is matched as if it were a standalone pattern at the current point, + and the longest match is then "locked in" for the rest of the overall + pattern. 2. When dealing with multiple paths through the tree simultaneously, it - is not straightforward to keep track of captured substrings for the - different matching possibilities, and PCRE's implementation of this + is not straightforward to keep track of captured substrings for the + different matching possibilities, and PCRE's implementation of this algorithm does not attempt to do this. This means that no captured sub- strings are available. - 3. Because no substrings are captured, back references within the pat- + 3. Because no substrings are captured, back references within the pat- tern are not supported, and cause errors if encountered. - 4. For the same reason, conditional expressions that use a backrefer- - ence as the condition are not supported. + 4. For the same reason, conditional expressions that use a backrefer- + ence as the condition or test for a specific group recursion are not + supported. + + 5. Because many paths through the tree may be active, the \K escape + sequence, which resets the start of the match when encountered (but may + be on some paths and not on others), is not supported. It causes an + error if encountered. - 5. Callouts are supported, but the value of the capture_top field is + 6. Callouts are supported, but the value of the capture_top field is always 1, and the value of the capture_last field is always -1. - 6. The \C escape sequence, which (in the standard algorithm) matches a - single byte, even in UTF-8 mode, is not supported because the DFA algo- - rithm moves through the subject string one character at a time, for all - active paths through the tree. + 7. The \C escape sequence, which (in the standard algorithm) matches a + single byte, even in UTF-8 mode, is not supported because the alterna- + tive algorithm moves through the subject string one character at a + time, for all active paths through the tree. + 8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) + are not supported. (*FAIL) is supported, and behaves like a failing + negative assertion. -ADVANTAGES OF THE DFA ALGORITHM - Using the DFA matching algorithm provides the following advantages: +ADVANTAGES OF THE ALTERNATIVE ALGORITHM + + Using the alternative matching algorithm provides the following advan- + tages: 1. All possible matches (at a single point in the subject) are automat- ically found, and in particular, the longest match is found. To find @@ -573,19 +753,19 @@ 2. There is much better support for partial matching. The restrictions on the content of the pattern that apply when using the standard algo- - rithm for partial matching do not apply to the DFA algorithm. For non- - anchored patterns, the starting position of a partial match is avail- - able. + rithm for partial matching do not apply to the alternative algorithm. + For non-anchored patterns, the starting position of a partial match is + available. - 3. Because the DFA algorithm scans the subject string just once, and - never needs to backtrack, it is possible to pass very long subject - strings to the matching function in several pieces, checking for par- - tial matching each time. + 3. Because the alternative algorithm scans the subject string just + once, and never needs to backtrack, it is possible to pass very long + subject strings to the matching function in several pieces, checking + for partial matching each time. -DISADVANTAGES OF THE DFA ALGORITHM +DISADVANTAGES OF THE ALTERNATIVE ALGORITHM - The DFA algorithm suffers from a number of disadvantages: + The alternative algorithm suffers from a number of disadvantages: 1. It is substantially slower than the standard algorithm. This is partly because it has to search for all possible matches, but is also @@ -593,12 +773,21 @@ 2. Capturing parentheses and back references are not supported. - 3. The "atomic group" feature of PCRE regular expressions is supported, - but does not provide the advantage that it does for the standard algo- - rithm. + 3. Although atomic groups are supported, their use does not provide the + performance advantage that it does for the standard algorithm. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + +REVISION + + Last updated: 19 April 2008 + Copyright (c) 1997-2008 University of Cambridge. ------------------------------------------------------------------------------ @@ -692,7 +881,7 @@ PCRE API OVERVIEW PCRE has its own native API, which is described in this document. There - is also a set of wrapper functions that correspond to the POSIX regular + are also some wrapper functions that correspond to the POSIX regular expression API. These are described in the pcreposix documentation. Both of these APIs define a set of C function calls. A C++ wrapper is distributed with PCRE. It is documented in the pcrecpp page. @@ -710,15 +899,15 @@ a Perl-compatible manner. A sample program that demonstrates the sim- plest way of using them is provided in the file called pcredemo.c in the source distribution. The pcresample documentation describes how to - run it. + compile and run it. A second matching function, pcre_dfa_exec(), which is not Perl-compati- ble, is also provided. This uses a different algorithm for the match- ing. The alternative algorithm finds all possible matches (at a given - point in the subject). However, this algorithm does not return captured - substrings. A description of the two matching algorithms and their - advantages and disadvantages is given in the pcrematching documenta- - tion. + point in the subject), and scans the subject just once. However, this + algorithm does not return captured substrings. A description of the two + matching algorithms and their advantages and disadvantages is given in + the pcrematching documentation. In addition to the main compiling and matching functions, there are convenience functions for extracting captured substrings from a subject @@ -779,16 +968,37 @@ NEWLINES - PCRE supports three different conventions for indicating line breaks in - strings: a single CR character, a single LF character, or the two-char- - acter sequence CRLF. All three are used as "standard" by different - operating systems. When PCRE is built, a default can be specified. The - default default is LF, which is the Unix standard. When PCRE is run, - the default can be overridden, either when a pattern is compiled, or - when it is matched. + + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- + feed) character, the two-character sequence CRLF, any of the three pre- + ceding, or any Unicode newline sequence. The Unicode newline sequences + are the three just mentioned, plus the single characters VT (vertical + tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line + separator, U+2028), and PS (paragraph separator, U+2029). + + Each of the first three conventions is used by at least one operating + system as its standard newline sequence. When PCRE is built, a default + can be specified. The default default is LF, which is the Unix stan- + dard. When PCRE is run, the default can be overridden, either when a + pattern is compiled, or when it is matched. + + At compile time, the newline convention can be specified by the options + argument of pcre_compile(), or it can be specified by special text at + the start of the pattern itself; this overrides any other settings. See + the pcrepattern page for details of the special character sequences. In the PCRE documentation the word "newline" is used to mean "the char- - acter or pair of characters that indicate a line break". + acter or pair of characters that indicate a line break". The choice of + newline convention affects the handling of the dot, circumflex, and + dollar metacharacters, the handling of #-comments in /x mode, and, when + CRLF is a recognized line ending sequence, the match position advance- + ment for a non-anchored pattern. There is more detail about this in the + section on pcre_exec() options below. + + The choice of newline convention does not affect the interpretation of + the \n or \r escape sequences, nor does it affect what \R matches, + which is controlled in a similar way, but by separate options. MULTITHREADING @@ -798,7 +1008,7 @@ pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the callout function pointed to by pcre_callout, are shared by all threads. - The compiled form of a regular expression is not altered during match- + The compiled form of a regular expression is not altered during match- ing, so the same compiled pattern can safely be used by several threads at once. @@ -806,68 +1016,81 @@ SAVING PRECOMPILED PATTERNS FOR LATER USE The compiled form of a regular expression can be saved and re-used at a - later time, possibly by a different program, and even on a host other - than the one on which it was compiled. Details are given in the - pcreprecompile documentation. + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation. However, compiling a regular expression + with one version of PCRE for use with a different version is not guar- + anteed to work and may cause crashes. CHECKING BUILD-TIME OPTIONS int pcre_config(int what, void *where); - The function pcre_config() makes it possible for a PCRE client to dis- + The function pcre_config() makes it possible for a PCRE client to dis- cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- + The pcrebuild documentation has more details about these optional fea- tures. - The first argument for pcre_config() is an integer, specifying which + The first argument for pcre_config() is an integer, specifying which information is required; the second argument is a pointer to a variable - into which the information is placed. The following information is + into which the information is placed. The following information is available: PCRE_CONFIG_UTF8 - The output is an integer that is set to one if UTF-8 support is avail- + The output is an integer that is set to one if UTF-8 support is avail- able; otherwise it is set to zero. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The three values that - are supported are: 10 for LF, 13 for CR, and 3338 for CRLF. The default - should normally be the standard sequence for your operating system. + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The four values that + are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, + and -1 for ANY. Though they are derived from ASCII, the same values + are returned in EBCDIC environments. The default should normally corre- + spond to the standard sequence for your operating system. + + PCRE_CONFIG_BSR + + The output is an integer whose value indicates what character sequences + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R + matches only CR, LF, or CRLF. The default can be overridden when a pat- + tern is compiled or matched. PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. The default value of 2 is sufficient - for all but the most massive patterns, since it allows the compiled + 4. Larger values allow larger regular expressions to be compiled, at + the expense of slower matching. The default value of 2 is sufficient + for all but the most massive patterns, since it allows the compiled pattern to be up to 64K in size. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are given in the pcreposix documentation. PCRE_CONFIG_MATCH_LIMIT - The output is an integer that gives the default limit for the number of - internal matching function calls in a pcre_exec() execution. Further - details are given with pcre_exec() below. + The output is a long integer that gives the default limit for the num- + ber of internal matching function calls in a pcre_exec() execution. + Further details are given with pcre_exec() below. PCRE_CONFIG_MATCH_LIMIT_RECURSION - The output is an integer that gives the default limit for the depth of - recursion when calling the internal matching function in a pcre_exec() - execution. Further details are given with pcre_exec() below. + The output is a long integer that gives the default limit for the depth + of recursion when calling the internal matching function in a + pcre_exec() execution. Further details are given with pcre_exec() + below. PCRE_CONFIG_STACKRECURSE @@ -909,39 +1132,40 @@ fully relocatable, because it may contain a copy of the tableptr argu- ment, which is an address (see below). - The options argument contains independent bits that affect the compila- - tion. It should be zero if no options are required. The available - options are described below. Some of them, in particular, those that - are compatible with Perl, can also be set and unset from within the - pattern (see the detailed description in the pcrepattern documenta- - tion). For these options, the contents of the options argument speci- - fies their initial settings at the start of compilation and execution. - The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time - of matching as well as at compile time. + The options argument contains various bit settings that affect the com- + pilation. It should be zero if no options are required. The available + options are described below. Some of them (in particular, those that + are compatible with Perl, but also some others) can also be set and + unset from within the pattern (see the detailed description in the + pcrepattern documentation). For those options that can be different in + different parts of the pattern, the contents of the options argument + specifies their initial settings at the start of compilation and execu- + tion. The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the + time of matching as well as at compile time. If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and + if compilation of a pattern fails, pcre_compile() returns NULL, and sets the variable pointed to by errptr to point to a textual error mes- sage. This is a static string that is part of the library. You must not try to free it. The offset from the start of the pattern to the charac- ter where the error was discovered is placed in the variable pointed to - by erroffset, which must not be NULL. If it is, an immediate error is + by erroffset, which must not be NULL. If it is, an immediate error is given. - If pcre_compile2() is used instead of pcre_compile(), and the error- - codeptr argument is not NULL, a non-zero error code number is returned - via this argument in the event of an error. This is in addition to the + If pcre_compile2() is used instead of pcre_compile(), and the error- + codeptr argument is not NULL, a non-zero error code number is returned + via this argument in the event of an error. This is in addition to the textual error message. Error codes and messages are listed below. - If the final argument, tableptr, is NULL, PCRE uses a default set of - character tables that are built when PCRE is compiled, using the - default C locale. Otherwise, tableptr must be an address that is the - result of a call to pcre_maketables(). This value is stored with the - compiled pattern, and used again by pcre_exec(), unless another table + If the final argument, tableptr, is NULL, PCRE uses a default set of + character tables that are built when PCRE is compiled, using the + default C locale. Otherwise, tableptr must be an address that is the + result of a call to pcre_maketables(). This value is stored with the + compiled pattern, and used again by pcre_exec(), unless another table pointer is passed to it. For more discussion, see the section on locale support below. - This code fragment shows a typical straightforward call to pcre_com- + This code fragment shows a typical straightforward call to pcre_com- pile(): pcre *re; @@ -954,96 +1178,122 @@ &erroffset, /* for error offset */ NULL); /* use default character tables */ - The following names for option bits are defined in the pcre.h header + The following names for option bits are defined in the pcre.h header file: PCRE_ANCHORED If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. PCRE_AUTO_CALLOUT If this bit is set, pcre_compile() automatically inserts callout items, - all with number 255, before each pattern item. For discussion of the + all with number 255, before each pattern item. For discussion of the callout facility, see the pcrecallout documentation. + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. The default is specified when + PCRE is built. It can be overridden from within the pattern, or by set- + ting an option when a compiled pattern is matched. + PCRE_CASELESS - If this bit is set, letters in the pattern match both upper and lower - case letters. It is equivalent to Perl's /i option, and it can be - changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE - always understands the concept of case for characters whose values are - less than 128, so caseless matching is always possible. For characters - with higher values, the concept of case is supported if PCRE is com- - piled with Unicode property support, but not otherwise. If you want to - use caseless matching for characters 128 and above, you must ensure - that PCRE is compiled with Unicode property support as well as with + If this bit is set, letters in the pattern match both upper and lower + case letters. It is equivalent to Perl's /i option, and it can be + changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE + always understands the concept of case for characters whose values are + less than 128, so caseless matching is always possible. For characters + with higher values, the concept of case is supported if PCRE is com- + piled with Unicode property support, but not otherwise. If you want to + use caseless matching for characters 128 and above, you must ensure + that PCRE is compiled with Unicode property support as well as with UTF-8 support. PCRE_DOLLAR_ENDONLY - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored - if PCRE_MULTILINE is set. There is no equivalent to this option in + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored + if PCRE_MULTILINE is set. There is no equivalent to this option in Perl, and no way to set it within a pattern. PCRE_DOTALL If this bit is set, a dot metacharater in the pattern matches all char- - acters, including those that indicate newline. Without it, a dot does - not match when the current position is at a newline. This option is - equivalent to Perl's /s option, and it can be changed within a pattern - by a (?s) option setting. A negative class such as [^a] always matches - newlines, independent of the setting of this option. + acters, including those that indicate newline. Without it, a dot does + not match when the current position is at a newline. This option is + equivalent to Perl's /s option, and it can be changed within a pattern + by a (?s) option setting. A negative class such as [^a] always matches + newline characters, independent of the setting of this option. PCRE_DUPNAMES - If this bit is set, names used to identify capturing subpatterns need + If this bit is set, names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also the pcrepattern documentation. PCRE_EXTENDED - If this bit is set, whitespace data characters in the pattern are + If this bit is set, whitespace data characters in the pattern are totally ignored except when escaped or inside a character class. White- space does not include the VT character (code 11). In addition, charac- ters between an unescaped # outside a character class and the next new- - line, inclusive, are also ignored. This is equivalent to Perl's /x - option, and it can be changed within a pattern by a (?x) option set- + line, inclusive, are also ignored. This is equivalent to Perl's /x + option, and it can be changed within a pattern by a (?x) option set- ting. - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + Whitespace characters may never appear within special character + sequences in a pattern, for example within the sequence (?( which introduces a conditional subpattern. PCRE_EXTRA - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a - literal. (Perl can, however, be persuaded to give a warning for this.) - There are at present no other features controlled by this option. It + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a + literal. (Perl can, however, be persuaded to give a warning for this.) + There are at present no other features controlled by this option. It can also be set by a (?X) option setting within a pattern. PCRE_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the matched text may continue over the newline. + PCRE_JAVASCRIPT_COMPAT + + If this option is set, PCRE's behaviour is changed in some ways so that + it is compatible with JavaScript rather than Perl. The changes are as + follows: + + (1) A lone closing square bracket in a pattern causes a compile-time + error, because this is illegal in JavaScript (by default it is treated + as a data character). Thus, the pattern AB]CD becomes illegal when this + option is set. + + (2) At run time, a back reference to an unset subpattern group matches + an empty string (by default this causes the current matching alterna- + tive to fail). A pattern such as (\1)(a) succeeds when this option is + set (assuming it can find an "a" in the subject), whereas it fails by + default, for Perl compatibility. + PCRE_MULTILINE By default, PCRE treats the subject string as consisting of a single @@ -1064,62 +1314,85 @@ PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY These options override the default newline definition that was chosen when PCRE was built. Setting the first or the second specifies that a newline is indicated by a single character (CR or LF, respectively). - Setting both of them specifies that a newline is indicated by the two- - character CRLF sequence. For convenience, PCRE_NEWLINE_CRLF is defined - to contain both bits. The only time that a line break is relevant when - compiling a pattern is if PCRE_EXTENDED is set, and an unescaped # out- - side a character class is encountered. This indicates a comment that - lasts until after the next newline. + Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the + two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies + that any of the three preceding sequences should be recognized. Setting + PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be + recognized. The Unicode newline sequences are the three just mentioned, + plus the single characters VT (vertical tab, U+000B), FF (formfeed, + U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS + (paragraph separator, U+2029). The last two are recognized only in + UTF-8 mode. + + The newline setting in the options word uses three bits that are + treated as a number, giving eight possibilities. Currently only six are + used (default plus the five values above). This means that if you set + more than one newline option, the combination may or may not be sensi- + ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to + PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and + cause an error. + + The only time that a line break is specially recognized when compiling + a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a + character class is encountered. This indicates a comment that lasts + until after the next line break sequence. In other circumstances, line + break sequences are treated as literal data, except that in + PCRE_EXTENDED mode, both CR and LF are treated as whitespace characters + and are therefore ignored. - The newline option set at compile time becomes the default that is used - for pcre_exec() and pcre_dfa_exec(), but it can be overridden. + The newline option that is set at compile time becomes the default that + is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. PCRE_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. PCRE_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE_UTF8 - This option causes PCRE to regard both the pattern and the subject as - strings of UTF-8 characters instead of single-byte character strings. - However, it is available only when PCRE is built to include UTF-8 sup- - port. If not, the use of this option provokes an error. Details of how - this option changes the behaviour of PCRE are given in the section on + This option causes PCRE to regard both the pattern and the subject as + strings of UTF-8 characters instead of single-byte character strings. + However, it is available only when PCRE is built to include UTF-8 sup- + port. If not, the use of this option provokes an error. Details of how + this option changes the behaviour of PCRE are given in the section on UTF-8 support in the main pcre page. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. If an invalid UTF-8 sequence of bytes is found, - pcre_compile() returns an error. If you already know that your pattern - is valid, and you want to skip this check for performance reasons, you - can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of - passing an invalid UTF-8 string as a pattern is undefined. It may cause - your program to crash. Note that this option can also be passed to - pcre_exec() and pcre_dfa_exec(), to suppress the UTF-8 validity check- - ing of subject strings. + automatically checked. There is a discussion about the validity of + UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of + bytes is found, pcre_compile() returns an error. If you already know + that your pattern is valid, and you want to skip this check for perfor- + mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is + set, the effect of passing an invalid UTF-8 string as a pattern is + undefined. It may cause your program to crash. Note that this option + can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the + UTF-8 validity checking of subject strings. COMPILATION ERROR CODES The following table lists the error codes than may be returned by pcre_compile2(), along with the error messages that may be returned by - both compiling functions. + both compiling functions. As PCRE has developed, some error codes have + fallen out of use. To avoid confusion, they have not been re-used. 0 no error 1 \ at end of pattern @@ -1131,17 +1404,17 @@ 7 invalid escape sequence in character class 8 range out of order in character class 9 nothing to repeat - 10 operand of unlimited repeat could match the empty string + 10 [this code is not in use] 11 internal error: unexpected repeat - 12 unrecognized character after (? + 12 unrecognized character after (? or (?- 13 POSIX named classes are supported only within a class 14 missing ) 15 reference to non-existent subpattern 16 erroffset passed as NULL 17 unknown option bit(s) set 18 missing ) after comment - 19 parentheses nested too deeply - 20 regular expression too large + 19 [this code is not in use] + 20 regular expression is too large 21 failed to get memory 22 unmatched parentheses 23 internal error: code overflow @@ -1150,11 +1423,11 @@ 26 malformed number or name after (?( 27 conditional group contains more than two branches 28 assertion expected after (?( - 29 (?R or (?digits must be followed by ) + 29 (?R or (?[+-]digits must be followed by ) 30 unknown POSIX class name 31 POSIX collating elements are not supported 32 this version of PCRE is not compiled with PCRE_UTF8 support - 33 spare error + 33 [this code is not in use] 34 character value in \x{...} sequence is too large 35 invalid condition (?(0) 36 \C not allowed in lookbehind assertion @@ -1163,16 +1436,34 @@ 39 closing ) for (?C expected 40 recursive call could loop indefinitely 41 unrecognized character after (?P - 42 syntax error after (?P + 42 syntax error in subpattern name (missing terminator) 43 two named subpatterns have the same name 44 invalid UTF-8 string 45 support for \P, \p, and \X has not been compiled 46 malformed \P or \p sequence 47 unknown property name after \P or \p 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10,000) - 50 repeated subpattern is too long + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] 51 octal value is greater than \377 (not in UTF-8 mode) + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern not + found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \g is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 (*VERB) with an argument is not supported + 60 (*VERB) not recognized + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode + + The numbers 32 and 10000 in errors 48 and 49 are defaults; different + values may be used if the limits were changed when PCRE was built. STUDYING A PATTERN @@ -1180,32 +1471,32 @@ pcre_extra *pcre_study(const pcre *code, int options const char **errptr); - If a compiled pattern is going to be used several times, it is worth + If a compiled pattern is going to be used several times, it is worth spending more time analyzing it in order to speed up the time taken for - matching. The function pcre_study() takes a pointer to a compiled pat- + matching. The function pcre_study() takes a pointer to a compiled pat- tern as its first argument. If studying the pattern produces additional - information that will help speed up matching, pcre_study() returns a - pointer to a pcre_extra block, in which the study_data field points to + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to the results of the study. The returned value from pcre_study() can be passed directly to - pcre_exec(). However, a pcre_extra block also contains other fields - that can be set by the caller before the block is passed; these are + pcre_exec(). However, a pcre_extra block also contains other fields + that can be set by the caller before the block is passed; these are described below in the section on matching a pattern. - If studying the pattern does not produce any additional information + If studying the pattern does not produce any additional information pcre_study() returns NULL. In that circumstance, if the calling program - wants to pass any of the other fields to pcre_exec(), it must set up + wants to pass any of the other fields to pcre_exec(), it must set up its own pcre_extra block. - The second argument of pcre_study() contains option bits. At present, + The second argument of pcre_study() contains option bits. At present, no options are defined, and this argument should always be zero. - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it is set to point to a textual + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual error message. This is a static string that is part of the library. You - must not try to free it. You should test the error pointer for NULL + must not try to free it. You should test the error pointer for NULL after calling pcre_study(), to be sure that it has run successfully. This is a typical call to pcre_study(): @@ -1217,26 +1508,33 @@ &error); /* set to NULL or points to a message */ At present, studying a pattern is useful only for non-anchored patterns - that do not have a single fixed starting character. A bitmap of possi- + that do not have a single fixed starting character. A bitmap of possi- ble starting bytes is created. LOCALE SUPPORT - PCRE handles caseless matching, and determines whether characters are - letters digits, or whatever, by reference to a set of tables, indexed - by character value. When running in UTF-8 mode, this applies only to - characters with codes less than 128. Higher-valued codes never match - escapes such as \w or \d, but can be tested with \p if PCRE is built - with Unicode character property support. The use of locales with Uni- - code is discouraged. - - An internal set of tables is created in the default C locale when PCRE - is built. This is used when the final argument of pcre_compile() is - NULL, and is sufficient for many applications. An alternative set of - tables can, however, be supplied. These may be created in a different - locale from the default. As more and more applications change to using - Unicode, the need for this locale support is expected to die away. + PCRE handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character value. When running in UTF-8 mode, this applies only to + characters with codes less than 128. Higher-valued codes never match + escapes such as \w or \d, but can be tested with \p if PCRE is built + with Unicode character property support. The use of locales with Uni- + code is discouraged. If you are handling characters with codes greater + than 128, you should either use UTF-8 and Unicode, or use locales, but + not try to mix the two. + + PCRE contains an internal set of tables that are used when the final + argument of pcre_compile() is NULL. These are sufficient for many + applications. Normally, the internal tables recognize only ASCII char- + acters. However, when PCRE is built, it is possible to cause the inter- + nal tables to be rebuilt in the default "C" locale of the local system, + which may cause them to be different. + + The internal tables can always be overridden by tables supplied by the + application that calls PCRE. These may be created in a different locale + from the default. As more and more applications change to using Uni- + code, the need for this locale support is expected to die away. External tables are built by calling the pcre_maketables() function, which has no arguments, in the relevant locale. The result can then be @@ -1249,20 +1547,23 @@ tables = pcre_maketables(); re = pcre_compile(..., tables); - When pcre_maketables() runs, the tables are built in memory that is - obtained via pcre_malloc. It is the caller's responsibility to ensure - that the memory containing the tables remains available for as long as + The locale name "fr_FR" is used on Linux and other Unix-like systems; + if you are using Windows, the name for the French locale is "french". + + When pcre_maketables() runs, the tables are built in memory that is + obtained via pcre_malloc. It is the caller's responsibility to ensure + that the memory containing the tables remains available for as long as it is needed. The pointer that is passed to pcre_compile() is saved with the compiled - pattern, and the same tables are used via this pointer by pcre_study() + pattern, and the same tables are used via this pointer by pcre_study() and normally also by pcre_exec(). Thus, by default, for any single pat- tern, compilation, studying and matching all happen in the same locale, but different patterns can be compiled in different locales. - It is possible to pass a table pointer or NULL (indicating the use of - the internal tables) to pcre_exec(). Although not intended for this - purpose, this facility could be used to match a pattern in a different + It is possible to pass a table pointer or NULL (indicating the use of + the internal tables) to pcre_exec(). Although not intended for this + purpose, this facility could be used to match a pattern in a different locale from the one in which it was compiled. Passing table pointers at run time is discussed below in the section on matching a pattern. @@ -1272,15 +1573,15 @@ int pcre_fullinfo(const pcre *code, const pcre_extra *extra, int what, void *where); - The pcre_fullinfo() function returns information about a compiled pat- + The pcre_fullinfo() function returns information about a compiled pat- tern. It replaces the obsolete pcre_info() function, which is neverthe- less retained for backwards compability (and is documented below). - The first argument for pcre_fullinfo() is a pointer to the compiled - pattern. The second argument is the result of pcre_study(), or NULL if - the pattern was not studied. The third argument specifies which piece - of information is required, and the fourth argument is a pointer to a - variable to receive the data. The yield of the function is zero for + The first argument for pcre_fullinfo() is a pointer to the compiled + pattern. The second argument is the result of pcre_study(), or NULL if + the pattern was not studied. The third argument specifies which piece + of information is required, and the fourth argument is a pointer to a + variable to receive the data. The yield of the function is zero for success, or one of the following negative numbers: PCRE_ERROR_NULL the argument code was NULL @@ -1288,9 +1589,9 @@ PCRE_ERROR_BADMAGIC the "magic number" was not found PCRE_ERROR_BADOPTION the value of what was invalid - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre_fullinfo(), to obtain the length of the compiled + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre_fullinfo(), to obtain the length of the compiled pattern: int rc; @@ -1301,56 +1602,69 @@ PCRE_INFO_SIZE, /* what is required */ &length); /* where to put the data */ - The possible values for the third argument are defined in pcre.h, and + The possible values for the third argument are defined in pcre.h, and are as follows: PCRE_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - fourth argument should point to an int variable. Zero is returned if + Return the number of the highest back reference in the pattern. The + fourth argument should point to an int variable. Zero is returned if there are no back references. PCRE_INFO_CAPTURECOUNT - Return the number of capturing subpatterns in the pattern. The fourth + Return the number of capturing subpatterns in the pattern. The fourth argument should point to an int variable. PCRE_INFO_DEFAULT_TABLES - Return a pointer to the internal default character tables within PCRE. - The fourth argument should point to an unsigned char * variable. This + Return a pointer to the internal default character tables within PCRE. + The fourth argument should point to an unsigned char * variable. This information call is provided for internal use by the pcre_study() func- - tion. External callers can cause PCRE to use its internal tables by + tion. External callers can cause PCRE to use its internal tables by passing a NULL table pointer. PCRE_INFO_FIRSTBYTE - Return information about the first byte of any matched string, for a - non-anchored pattern. The fourth argument should point to an int vari- - able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name + Return information about the first byte of any matched string, for a + non-anchored pattern. The fourth argument should point to an int vari- + able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is still recognized for backwards compatibility.) - If there is a fixed first byte, for example, from a pattern such as - (cat|cow|coyote). Otherwise, if either + If there is a fixed first byte, for example, from a pattern such as + (cat|cow|coyote), its value is returned. Otherwise, if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set (if it were set, the pattern would be anchored), - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. PCRE_INFO_FIRSTTABLE - If the pattern was studied, and this resulted in the construction of a + If the pattern was studied, and this resulted in the construction of a 256-bit table indicating a fixed set of bytes for the first byte in any - matching string, a pointer to the table is returned. Otherwise NULL is - returned. The fourth argument should point to an unsigned char * vari- + matching string, a pointer to the table is returned. Otherwise NULL is + returned. The fourth argument should point to an unsigned char * vari- able. + PCRE_INFO_HASCRORLF + + Return 1 if the pattern contains any explicit matches for CR or LF + characters, otherwise 0. The fourth argument should point to an int + variable. An explicit match is either a literal CR or LF character, or + \r or \n. + + PCRE_INFO_JCHANGED + + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The fourth argument should point to an int variable. (?J) + and (?-J) set and unset the local PCRE_DUPNAMES option, respectively. + PCRE_INFO_LASTLITERAL Return the value of the rightmost literal byte that must exist in any @@ -1388,8 +1702,8 @@ PCRE_EXTENDED is set, so white space - including newlines - is ignored): - (?P<date> (?P<year>(\d\d)?\d\d) - - (?P<month>\d\d) - (?P<day>\d\d) ) + (?<date> (?<year>(\d\d)?\d\d) - + (?<month>\d\d) - (?<day>\d\d) ) There are four named subpatterns, so the table has four entries, and each entry in the table is eight bytes long. The table is as follows, @@ -1405,14 +1719,25 @@ name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. + PCRE_INFO_OKPARTIAL + + Return 1 if the pattern can be used for partial matching, otherwise 0. + The fourth argument should point to an int variable. The pcrepartial + documentation lists the restrictions that apply to patterns when par- + tial matching is used. + PCRE_INFO_OPTIONS - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These option bits are those specified in the call to pcre_compile(), modified - by any top-level option settings within the pattern itself. + by any top-level option settings at the start of the pattern itself. In + other words, they are the options that will be in force when matching + starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with + the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, + and PCRE_EXTENDED. - A pattern is automatically anchored by PCRE if all of its top-level + A pattern is automatically anchored by PCRE if all of its top-level alternatives begin with one of the following: ^ unless PCRE_MULTILINE is set @@ -1426,7 +1751,7 @@ PCRE_INFO_SIZE - Return the size of the compiled pattern, that is, the value that was + Return the size of the compiled pattern, that is, the value that was passed as the argument to pcre_malloc() when PCRE was getting memory in which to place the compiled data. The fourth argument should point to a size_t variable. @@ -1434,9 +1759,9 @@ PCRE_INFO_STUDYSIZE Return the size of the data block pointed to by the study_data field in - a pcre_extra block. That is, it is the value that was passed to + a pcre_extra block. That is, it is the value that was passed to pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t + created by pcre_study(). The fourth argument should point to a size_t variable. @@ -1444,21 +1769,21 @@ int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- + The pcre_info() function is now obsolete because its interface is too + restrictive to return all the available data about a compiled pattern. + New programs should use pcre_fullinfo() instead. The yield of + pcre_info() is the number of capturing subpatterns, or one of the fol- lowing negative numbers: PCRE_ERROR_NULL the argument code was NULL PCRE_ERROR_BADMAGIC the "magic number" was not found - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see + If the optptr argument is not NULL, a copy of the options with which + the pattern was compiled is placed in the integer it points to (see PCRE_INFO_OPTIONS above). - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of + If the pattern is not anchored and the firstcharptr argument is not + NULL, it is used to pass back information about the first character of any matched string (see PCRE_INFO_FIRSTBYTE above). @@ -1466,21 +1791,21 @@ int pcre_refcount(pcre *code, int adjust); - The pcre_refcount() function is used to maintain a reference count in + The pcre_refcount() function is used to maintain a reference count in the data block that contains a compiled pattern. It is provided for the - benefit of applications that operate in an object-oriented manner, + benefit of applications that operate in an object-oriented manner, where different parts of the application may be using the same compiled pattern, but you want to free the block when they are all done. When a pattern is compiled, the reference count field is initialized to - zero. It is changed only by calling this function, whose action is to - add the adjust value (which may be positive or negative) to it. The + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The yield of the function is the new value. However, the value of the count - is constrained to lie between 0 and 65535, inclusive. If the new value + is constrained to lie between 0 and 65535, inclusive. If the new value is outside these limits, it is forced to the appropriate limit value. - Except when it is zero, the reference count is not correctly preserved - if a pattern is compiled on one host and then transferred to a host + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host whose byte-order is different. (This seems a highly unlikely scenario.) @@ -1574,53 +1899,89 @@ the total number of calls, because not all calls to match() are recur- sive. This limit is of use only if it is set smaller than match_limit. - Limiting the recursion depth limits the amount of stack that can be + Limiting the recursion depth limits the amount of stack that can be used, or, when PCRE has been compiled to use memory on the heap instead of the stack, the amount of heap memory that can be used. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - The pcre_callout field is used in conjunction with the "callout" fea- + The pcre_callout field is used in conjunction with the "callout" fea- ture, which is described in the pcrecallout documentation. - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- + The tables field is used to pass a character tables pointer to + pcre_exec(); this overrides the value that is stored with the compiled + pattern. A non-NULL value is stored with the compiled pattern only if + custom tables were supplied to pcre_compile() via its tableptr argu- ment. If NULL is passed to pcre_exec() using this mechanism, it forces - PCRE's internal tables to be used. This facility is helpful when re- - using patterns that have been saved after compiling with an external - set of tables, because the external tables might be at a different - address when pcre_exec() is called. See the pcreprecompile documenta- + PCRE's internal tables to be used. This facility is helpful when re- + using patterns that have been saved after compiling with an external + set of tables, because the external tables might be at a different + address when pcre_exec() is called. See the pcreprecompile documenta- tion for a discussion of saving compiled patterns for later use. Option bits for pcre_exec() - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, - PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and - PCRE_PARTIAL. + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, + PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the + choice that was made or defaulted when the pattern was compiled. + PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY These options override the newline definition that was chosen or defaulted when the pattern was compiled. For details, see the descrip- - tion pcre_compile() above. During matching, the newline choice affects - the behaviour of the dot, circumflex, and dollar metacharacters. + tion of pcre_compile() above. During matching, the newline choice + affects the behaviour of the dot, circumflex, and dollar metacharac- + ters. It may also alter the way the match position is advanced after a + match failure for an unanchored pattern. + + When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is + set, and a match attempt for an unanchored pattern fails when the cur- + rent position is at a CRLF sequence, and the pattern contains no + explicit matches for CR or LF characters, the match position is + advanced by two characters instead of one, in other words, to after the + CRLF. + + The above rule is a compromise that makes the most common cases work as + expected. For example, if the pattern is .+A (and the PCRE_DOTALL + option is not set), it does not match the string "\r\nA" because, after + failing at the start, it skips both the CR and the LF before retrying. + However, the pattern [\r\n]A does match that string, because it con- + tains an explicit CR or LF reference, and so advances only by one char- + acter after the first failure. + + An explicit match for CR of LF is either a literal appearance of one of + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and + LF in the characters that it matches). + + Notwithstanding the above, anomalous effects may still occur when CRLF + is a valid newline sequence and explicit \r or \n escapes appear in the + pattern. PCRE_NOTBOL @@ -1662,15 +2023,27 @@ an ordinary match again. There is some code that demonstrates how to do this in the pcredemo.c sample program. + PCRE_NO_START_OPTIMIZE + + There are a number of optimizations that pcre_exec() uses at the start + of a match, in order to speed up the process. For example, if it is + known that a match must start with a specific character, it searches + the subject for that character, and fails immediately if it cannot find + it, without actually running the main matching function. When callouts + are in use, these optimizations can cause them to be skipped. This + option disables the "start-up" optimizations, causing performance to + suffer, but ensuring that the callouts do occur. + PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently - called. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. If an invalid UTF-8 sequence - of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8. If - startoffset contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is - returned. + UTF-8 string is automatically checked when pcre_exec() is subsequently + called. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the section on UTF-8 support in the + main pcre page. If an invalid UTF-8 sequence of bytes is found, + pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- + tains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. If you already know that your subject is valid, and you want to skip these checks for performance reasons, you can set the @@ -1697,83 +2070,87 @@ The string to be matched by pcre_exec() The subject string is passed to pcre_exec() as a pointer in subject, a - length in length, and a starting byte offset in startoffset. In UTF-8 - mode, the byte offset must point to the start of a UTF-8 character. - Unlike the pattern string, the subject may contain binary zero bytes. - When the starting offset is zero, the search for a match starts at the - beginning of the subject, and this is by far the most common case. - - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + length (in bytes) in length, and a starting byte offset in startoffset. + In UTF-8 mode, the byte offset must point to the start of a UTF-8 char- + acter. Unlike the pattern string, the subject may contain binary zero + bytes. When the starting offset is zero, the search for a match starts + at the beginning of the subject, and this is by far the most common + case. + + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire + to be a word boundary. However, if pcre_exec() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - If a non-zero starting offset is passed when the pattern is anchored, + If a non-zero starting offset is passed when the pattern is anchored, one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the + if the pattern does not require the match to be at the start of the subject. How pcre_exec() returns captured substrings - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. - Captured substrings are returned to the caller via a vector of integer - offsets whose address is passed in ovector. The number of elements in - the vector is passed in ovecsize, which must be a non-negative number. - Note: this argument is NOT the size of ovector in bytes. - - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The length passed in ovecsize should always be a multiple of three. If + Captured substrings are returned to the caller via a vector of integers + whose address is passed in ovector. The number of elements in the vec- + tor is passed in ovecsize, which must be a non-negative number. Note: + this argument is NOT the size of ovector in bytes. + + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The number passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of a pair is set to the offset of the first character in a sub- - string, and the second is set to the offset of the first character - after the end of a substring. The first pair, ovector[0] and ovec- - tor[1], identify the portion of the subject string matched by the - entire pattern. The next pair is used for the first capturing subpat- - tern, and so on. The value returned by pcre_exec() is one more than the - highest numbered pair that has been set. For example, if two substrings - have been captured, the returned value is 3. If there are no capturing - subpatterns, the return value from a successful match is 1, indicating - that just the first pair of offsets has been set. + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of each pair is set to the byte offset of the first character + in a substring, and the second is set to the byte offset of the first + character after the end of a substring. Note: these values are always + byte offsets, even in UTF-8 mode. They are not character counts. + + The first pair of integers, ovector[0] and ovector[1], identify the + portion of the subject string matched by the entire pattern. The next + pair is used for the first capturing subpattern, and so on. The value + returned by pcre_exec() is one more than the highest numbered pair that + has been set. For example, if two substrings have been captured, the + returned value is 3. If there are no capturing subpatterns, the return + value from a successful match is 1, indicating that just the first pair + of offsets has been set. If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. In particular, if the substring off- - sets are not of interest, pcre_exec() may be called with ovector passed - as NULL and ovecsize as zero. However, if the pattern contains back - references and the ovector is not big enough to remember the related - substrings, PCRE has to get additional memory for use during matching. - Thus it is usually advisable to supply an ovector. + function returns a value of zero. If the substring offsets are not of + interest, pcre_exec() may be called with ovector passed as NULL and + ovecsize as zero. However, if the pattern contains back references and + the ovector is not big enough to remember the related substrings, PCRE + has to get additional memory for use during matching. Thus it is usu- + ally advisable to supply an ovector. The pcre_info() function can be used to find out how many capturing subpatterns there are in a compiled pattern. The smallest size for @@ -1824,7 +2201,7 @@ an environment with the other endianness. This is the error that PCRE gives when the magic number is not present. - PCRE_ERROR_UNKNOWN_NODE (-5) + PCRE_ERROR_UNKNOWN_OPCODE (-5) While running the pattern match, an unknown item was encountered in the compiled pattern. This error could be caused by a bug in PCRE or by @@ -1850,12 +2227,6 @@ pcre_extra structure (or defaulted) was reached. See the description above. - PCRE_ERROR_RECURSIONLIMIT (-21) - - The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the - description above. - PCRE_ERROR_CALLOUT (-9) This error is never generated by pcre_exec() itself. It is provided for @@ -1891,7 +2262,19 @@ PCRE_ERROR_BADCOUNT (-15) - This error is given if the value of the ovecsize argument is negative. + This error is given if the value of the ovecsize argument is negative. + + PCRE_ERROR_RECURSIONLIMIT (-21) + + The internal recursion limit, as specified by the match_limit_recursion + field in a pcre_extra structure (or defaulted) was reached. See the + description above. + + PCRE_ERROR_BADNEWLINE (-23) + + An invalid combination of PCRE_NEWLINE_xxx options was given. + + Error numbers -16 to -20 and -22 are not used by pcre_exec(). EXTRACTING CAPTURED SUBSTRINGS BY NUMBER @@ -1907,57 +2290,58 @@ int pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr); - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named substrings. - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the + not adequate for handling strings containing binary zeros, because the end of the final string is not independently indicated. - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully matched, ovector is a pointer to the vector of integer offsets that was passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the + were captured by the match, including the substring that matched the entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should be the number of elements in the vector divided by three. - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including - the terminating zero, or one of + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including + the terminating zero, or one of these error codes: PCRE_ERROR_NOMEMORY (-6) - The buffer was too small for pcre_copy_substring(), or the attempt to + The buffer was too small for pcre_copy_substring(), or the attempt to get memory failed for pcre_get_substring(). PCRE_ERROR_NOSUBSTRING (-7) There is no substring whose number is stringnumber. - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the + error code PCRE_ERROR_NOMEMORY (-6) @@ -1999,7 +2383,7 @@ To extract a substring by name, you first have to find associated num- ber. For example, for this pattern - (a+)b(?P<xxx>\d+)... + (a+)b(?<xxx>\d+)... the number of the subpattern called "xxx" is 2. If the name is known to be unique (PCRE_DUPNAMES was not set), you can find the number from the @@ -2025,7 +2409,13 @@ These functions call pcre_get_stringnumber(), and if it succeeds, they then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + behaviour may not be what you want (see the next section). + + Warning: If the pattern uses the "(?|" feature to set up multiple sub- + patterns with the same number, you cannot use names to distinguish + them, because names are not included in the compiled code. The matching + process uses only numbers. DUPLICATE SUBPATTERN NAMES @@ -2037,12 +2427,14 @@ subpatterns are not required to be unique. Normally, patterns with duplicate names are such that in any one match, only one of the named subpatterns participates. An example is shown in the pcrepattern docu- - mentation. When duplicates are present, pcre_copy_named_substring() and + mentation. + + When duplicates are present, pcre_copy_named_substring() and pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, an empty string is - returned. The pcre_get_stringnumber() function returns one of the num- - bers that are associated with the name, but it is not defined which it - is. + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, + but it is not defined which it is. If you want to get full details of all captured substrings for a given name, you must use the pcre_get_stringtable_entries() function. The @@ -2050,11 +2442,11 @@ third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING if there - are none. The format of the table is described above in the section - entitled Information about a pattern. Given all the relevant entries - for the name, you can extract each of their numbers, and hence the cap- - tured data, if any. + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern. Given all the relevant + entries for the name, you can extract each of their numbers, and hence + the captured data, if any. FINDING ALL POSSIBLE MATCHES @@ -2083,23 +2475,24 @@ int *workspace, int wscount); The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a "DFA" matching algorithm. This has - different characteristics to the normal algorithm, and is not compati- - ble with Perl. Some of the features of PCRE patterns are not supported. - Nevertheless, there are times when this kind of matching can be useful. - For a discussion of the two matching algorithms, see the pcrematching - documentation. + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, see the pcrematching docu- + mentation. - The arguments for the pcre_dfa_exec() function are the same as for + The arguments for the pcre_dfa_exec() function are the same as for pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a + workspace will be needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre_dfa_exec(): @@ -2121,47 +2514,47 @@ Option bits for pcre_dfa_exec() - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- - LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are the same as for pcre_exec(), so their description is not repeated here. PCRE_PARTIAL - This has the same general effect as it does for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL is set for - pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into - PCRE_ERROR_PARTIAL if the end of the subject is reached, there have + This has the same general effect as it does for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL is set for + pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into + PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no complete matches, but there is still at least one matching pos- - sibility. The portion of the string that provided the partial match is + sibility. The portion of the string that provided the partial match is set as the first matching string. PCRE_DFA_SHORTEST - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to - stop as soon as it has found one match. Because of the way the DFA - algorithm works, this is necessarily the shortest possible match at the - first possible matching point in the subject string. + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + stop as soon as it has found one match. Because of the way the alterna- + tive algorithm works, this is necessarily the shortest possible match + at the first possible matching point in the subject string. PCRE_DFA_RESTART - When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and - returns a partial match, it is possible to call it again, with addi- - tional subject characters, and have it continue with the same match. - The PCRE_DFA_RESTART option requests this action; when it is set, the - workspace and wscount options must reference the same vector as before - because data about the match so far is left in them after a partial - match. There is more discussion of this facility in the pcrepartial + When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and + returns a partial match, it is possible to call it again, with addi- + tional subject characters, and have it continue with the same match. + The PCRE_DFA_RESTART option requests this action; when it is set, the + workspace and wscount options must reference the same vector as before + because data about the match so far is left in them after a partial + match. There is more discussion of this facility in the pcrepartial documentation. Successful returns from pcre_dfa_exec() - When pcre_dfa_exec() succeeds, it may have matched more than one sub- + When pcre_dfa_exec() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -2176,59 +2569,75 @@ <something> <something else> <something> <something else> <something further> - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. All - the strings have the same start offset. (Space could have been saved by - giving this only once, but it was decided to retain some compatibility - with the way pcre_exec() returns data, even though the meaning of the - strings is different.) + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the + meaning of the strings is different.) The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is filled with the longest matches. Error returns from pcre_dfa_exec() - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are specific to pcre_dfa_exec(): PCRE_ERROR_DFA_UITEM (-16) - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back reference. PCRE_ERROR_DFA_UCOND (-17) - This return is given if pcre_dfa_exec() encounters a condition item in - a pattern that uses a back reference for the condition. This is not - supported. + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion + in a specific group. These are not supported. PCRE_ERROR_DFA_UMLIMIT (-18) - This return is given if pcre_dfa_exec() is called with an extra block + This return is given if pcre_dfa_exec() is called with an extra block that contains a setting of the match_limit field. This is not supported (it is meaningless). PCRE_ERROR_DFA_WSSIZE (-19) - This return is given if pcre_dfa_exec() runs out of space in the + This return is given if pcre_dfa_exec() runs out of space in the workspace vector. PCRE_ERROR_DFA_RECURSE (-20) - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. -Last updated: 08 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + +SEE ALSO + + pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- + tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 11 April 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -2255,7 +2664,7 @@ default value is zero. For example, this pattern has two callout points: - (?C1)eabc(?C2)def + (?C1)abc(?C2)def If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is called, PCRE automatically inserts callouts, all with number 255, @@ -2279,8 +2688,8 @@ MISSING CALLOUTS You should be aware that, because of optimizations in the way PCRE - matches patterns, callouts sometimes do not happen. For example, if the - pattern is + matches patterns by default, callouts sometimes do not happen. For + example, if the pattern is ab(?C4)cd @@ -2289,13 +2698,18 @@ ever start, and the callout is never reached. However, with "abyd", though the result is still no match, the callout is obeyed. + You can disable these optimizations by passing the PCRE_NO_START_OPTI- + MIZE option to pcre_exec() or pcre_dfa_exec(). This slows down the + matching process, but does ensure that callouts such as the example + above are obeyed. + THE CALLOUT INTERFACE - During matching, when PCRE reaches a callout point, the external func- - tion defined by pcre_callout is called (if it is set). This applies to - both the pcre_exec() and the pcre_dfa_exec() matching functions. The - only argument to the callout function is a pointer to a pcre_callout + During matching, when PCRE reaches a callout point, the external func- + tion defined by pcre_callout is called (if it is set). This applies to + both the pcre_exec() and the pcre_dfa_exec() matching functions. The + only argument to the callout function is a pointer to a pcre_callout block. This structure contains the following fields: int version; @@ -2311,9 +2725,9 @@ int pattern_position; int next_item_length; - The version field is an integer containing the version number of the - block format. The initial version was 0; the current version is 1. The - version number will change again in future if additional fields are + The version field is an integer containing the version number of the + block format. The initial version was 0; the current version is 1. The + version number will change again in future if additional fields are added, but the intention is never to remove any of the existing fields. The callout_number field contains the number of the callout, as com- @@ -2330,10 +2744,12 @@ The subject and subject_length fields contain copies of the values that were passed to pcre_exec(). - The start_match field contains the offset within the subject at which - the current match attempt started. If the pattern is not anchored, the - callout function may be called several times from the same point in the - pattern for different starting points in the subject. + The start_match field normally contains the offset within the subject + at which the current match attempt started. However, if the escape + sequence \K has been encountered, this value is changed to reflect the + modified starting point. If the pattern is not anchored, the callout + function may be called several times from the same point in the pattern + for different starting points in the subject. The current_position field contains the offset within the subject of the current match pointer. @@ -2386,8 +2802,18 @@ reserved for use by callout functions; it will never be used by PCRE itself. -Last updated: 28 February 2005 -Copyright (c) 1997-2005 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 15 March 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -2401,45 +2827,46 @@ DIFFERENCES BETWEEN PCRE AND PERL This document describes the differences in the ways that PCRE and Perl - handle regular expressions. The differences described here are with - respect to Perl 5.8. + handle regular expressions. The differences described here are mainly + with respect to Perl 5.8, though PCRE versions 7.0 and later contain + some features that are expected to be in the forthcoming Perl 5.10. - 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details - of what it does have are given in the section on UTF-8 support in the + 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details + of what it does have are given in the section on UTF-8 support in the main pcre page. 2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl - permits them, but they do not mean what you might think. For example, + permits them, but they do not mean what you might think. For example, (?!a){3} does not assert that the next three characters are not "a". It just asserts that the next character is not "a" three times. - 3. Capturing subpatterns that occur inside negative lookahead asser- - tions are counted, but their entries in the offsets vector are never - set. Perl sets its numerical variables from any such patterns that are + 3. Capturing subpatterns that occur inside negative lookahead asser- + tions are counted, but their entries in the offsets vector are never + set. Perl sets its numerical variables from any such patterns that are matched before the assertion fails to match something (thereby succeed- - ing), but only if the negative lookahead assertion contains just one + ing), but only if the negative lookahead assertion contains just one branch. - 4. Though binary zero characters are supported in the subject string, + 4. Though binary zero characters are supported in the subject string, they are not allowed in a pattern string because it is passed as a nor- mal C string, terminated by zero. The escape sequence \0 can be used in the pattern to represent a binary zero. - 5. The following Perl escape sequences are not supported: \l, \u, \L, + 5. The following Perl escape sequences are not supported: \l, \u, \L, \U, and \N. In fact these are implemented by Perl's general string-han- - dling and are not part of its pattern matching engine. If any of these + dling and are not part of its pattern matching engine. If any of these are encountered by PCRE, an error is generated. - 6. The Perl escape sequences \p, \P, and \X are supported only if PCRE - is built with Unicode character property support. The properties that - can be tested with \p and \P are limited to the general category prop- - erties such as Lu and Nd, script names such as Greek or Han, and the + 6. The Perl escape sequences \p, \P, and \X are supported only if PCRE + is built with Unicode character property support. The properties that + can be tested with \p and \P are limited to the general category prop- + erties such as Lu and Nd, script names such as Greek or Han, and the derived properties Any and L&. 7. PCRE does support the \Q...\E escape for quoting substrings. Charac- - ters in between are treated as literals. This is slightly different - from Perl in that $ and @ are also handled as literals inside the - quotes. In Perl, they cause variable interpolation (but of course PCRE + ters in between are treated as literals. This is slightly different + from Perl in that $ and @ are also handled as literals inside the + quotes. In Perl, they cause variable interpolation (but of course PCRE does not have variables). Note the following examples: Pattern PCRE matches Perl matches @@ -2449,67 +2876,85 @@ \Qabc\$xyz\E abc\$xyz abc\$xyz \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - The \Q...\E sequence is recognized both inside and outside character + The \Q...\E sequence is recognized both inside and outside character classes. - 8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) - constructions. However, there is support for recursive patterns using - the non-Perl items (?R), (?number), and (?P>name). Also, the PCRE - "callout" feature allows an external function to be called during pat- + 8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) + constructions. However, there is support for recursive patterns. This + is not available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE + "callout" feature allows an external function to be called during pat- tern matching. See the pcrecallout documentation for details. - 9. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 + 9. Subpatterns that are called recursively or as "subroutines" are + always treated as atomic groups in PCRE. This is like Python, but + unlike Perl. + + 10. There are some differences that are concerned with the settings of + captured strings when part of a pattern is repeated. For example, + matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". - 10. PCRE provides some extensions to the Perl regular expression facil- - ities: + 11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), + (*FAIL), (*F), (*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in + the forms without an argument. PCRE does not support (*MARK). If + (*ACCEPT) is within capturing parentheses, PCRE does not set that cap- + ture group; this is different to Perl. + + 12. PCRE provides some extensions to the Perl regular expression facil- + ities. Perl 5.10 will include new features that are not in earlier + versions, some of which (such as named parentheses) have been in PCRE + for some time. This list is with respect to Perl 5.10: - (a) Although lookbehind assertions must match fixed length strings, + (a) Although lookbehind assertions must match fixed length strings, each alternative branch of a lookbehind assertion can match a different length of string. Perl requires them all to have the same length. - (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ + (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta-character matches only at the very end of the string. (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- - cial meaning is faulted. Otherwise, like Perl, the backslash is - ignored. (Perl can be made to issue a warning.) + cial meaning is faulted. Otherwise, like Perl, the backslash is quietly + ignored. (Perl can be made to issue a warning.) - (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- + (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- fiers is inverted, that is, by default they are not greedy, but if fol- lowed by a question mark they are. (e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried only at the first matching position in the subject string. - (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- + (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- TURE options for pcre_exec() have no Perl equivalents. - (g) The (?R), (?number), and (?P>name) constructs allows for recursive - pattern matching (Perl can do this using the (?p{code}) construct, - which PCRE cannot support.) + (g) The \R escape sequence can be restricted to match only CR, LF, or + CRLF by the PCRE_BSR_ANYCRLF option. - (h) PCRE supports named capturing substrings, using the Python syntax. + (h) The callout facility is PCRE-specific. - (i) PCRE supports the possessive quantifier "++" syntax, taken from - Sun's Java package. + (i) The partial matching facility is PCRE-specific. - (j) The (R) condition, for testing recursion, is a PCRE extension. + (j) Patterns compiled by PCRE can be saved and re-used at a later time, + even on different hosts that have the other endianness. - (k) The callout facility is PCRE-specific. + (k) The alternative matching function (pcre_dfa_exec()) matches in a + different way and is not Perl-compatible. - (l) The partial matching facility is PCRE-specific. + (l) PCRE recognizes some special sequences such as (*CR) at the start + of a pattern that set overall options that cannot be changed within the + pattern. - (m) Patterns compiled by PCRE can be saved and re-used at a later time, - even on different hosts that have the other endianness. - (n) The alternative matching function (pcre_dfa_exec()) matches in a - different way and is not Perl-compatible. +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + +REVISION + + Last updated: 11 September 2007 + Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -2522,55 +2967,110 @@ PCRE REGULAR EXPRESSION DETAILS - The syntax and semantics of the regular expressions supported by PCRE - are described below. Regular expressions are also described in the Perl - documentation and in a number of books, some of which have copious - examples. Jeffrey Friedl's "Mastering Regular Expressions", published - by O'Reilly, covers regular expressions in great detail. This descrip- - tion of PCRE's regular expressions is intended as reference material. + The syntax and semantics of the regular expressions that are supported + by PCRE are described in detail below. There is a quick-reference syn- + tax summary in the pcresyntax page. PCRE tries to match Perl syntax and + semantics as closely as it can. PCRE also supports some alternative + regular expression syntax (which does not conflict with the Perl syn- + tax) in order to provide some compatibility with regular expressions in + Python, .NET, and Oniguruma. + + Perl's regular expressions are described in its own documentation, and + regular expressions in general are covered in a number of books, some + of which have copious examples. Jeffrey Friedl's "Mastering Regular + Expressions", published by O'Reilly, covers regular expressions in + great detail. This description of PCRE's regular expressions is + intended as reference material. The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 character strings. To use this, you must build PCRE to include UTF-8 support, and then call - pcre_compile() with the PCRE_UTF8 option. How this affects pattern - matching is mentioned in several places below. There is also a summary - of UTF-8 features in the section on UTF-8 support in the main pcre - page. + pcre_compile() with the PCRE_UTF8 option. There is also a special + sequence that can be given at the start of a pattern: + + (*UTF8) + + Starting a pattern with this sequence is equivalent to setting the + PCRE_UTF8 option. This feature is not Perl-compatible. How setting + UTF-8 mode affects pattern matching is mentioned in several places + below. There is also a summary of UTF-8 features in the section on + UTF-8 support in the main pcre page. The remainder of this document discusses the patterns that are sup- ported by PCRE when its main matching function, pcre_exec(), is used. From release 6.0, PCRE offers a second matching function, pcre_dfa_exec(), which matches using a different algorithm that is not - Perl-compatible. The advantages and disadvantages of the alternative - function, and how it differs from the normal function, are discussed in - the pcrematching page. - - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a + Perl-compatible. Some of the features discussed below are not available + when pcre_dfa_exec() is used. The advantages and disadvantages of the + alternative function, and how it differs from the normal function, are + discussed in the pcrematching page. + + +NEWLINE CONVENTIONS + + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- + feed) character, the two-character sequence CRLF, any of the three pre- + ceding, or any Unicode newline sequence. The pcreapi page has further + discussion about newlines, and shows how to set the newline convention + in the options arguments for the compiling and matching functions. + + It is also possible to specify a newline convention by starting a pat- + tern string with one of the following five sequences: + + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences + + These override the default and the options given to pcre_compile(). For + example, on a Unix system where LF is the default newline sequence, the + pattern + + (*CR)a.b + + changes the convention to CR. That pattern matches "a\nb" because LF is + no longer a newline. Note that these special settings, which are not + Perl-compatible, are recognized only at the very start of a pattern, + and that they must be in upper case. If more than one of them is + present, the last one is used. + + The newline convention does not affect what the \R escape sequence + matches. By default, this is any Unicode newline sequence, for Perl + compatibility. However, this can be changed; see the description of \R + in the section entitled "Newline sequences" below. A change of \R set- + ting can be combined with a change of newline convention. + + +CHARACTERS AND METACHARACTERS + + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a trivial example, the pattern The quick brown fox matches a portion of a subject string that is identical to itself. When - caseless matching is specified (the PCRE_CASELESS option), letters are - matched independently of case. In UTF-8 mode, PCRE always understands - the concept of case for characters whose values are less than 128, so - caseless matching is always possible. For characters with higher val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In UTF-8 mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is compiled with Unicode property support as well as with UTF-8 support. - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the pattern by the use of metacharacters, which do not stand for themselves but instead are interpreted in some special way. - There are two different sets of metacharacters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized in square brackets. Outside square brackets, the - metacharacters are as follows: + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized within square brackets. Outside square brackets, + the metacharacters are as follows: \ general escape character with several uses ^ assert start of string (or line, in multiline mode) @@ -2588,7 +3088,7 @@ also "possessive quantifier" { start min/max quantifier - Part of a pattern that is in square brackets is called a "character + Part of a pattern that is in square brackets is called a "character class". In a character class the only metacharacters are: \ general escape character @@ -2598,7 +3098,7 @@ syntax) ] terminates the character class - The following sections describe the use of each of the metacharacters. + The following sections describe the use of each of the metacharacters. BACKSLASH @@ -2650,7 +3150,7 @@ \cx "control-x", where x is any character \e escape (hex 1B) \f formfeed (hex 0C) - \n newline (hex 0A) + \n linefeed (hex 0A) \r carriage return (hex 0D) \t tab (hex 09) \ddd character with octal code ddd, or backreference @@ -2665,37 +3165,40 @@ After \x, from zero to two hexadecimal digits are read (letters can be in upper or lower case). Any number of hexadecimal digits may appear between \x{ and }, but the value of the character code must be less - than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode (that is, - the maximum hexadecimal value is 7FFFFFFF). If characters other than - hexadecimal digits appear between \x{ and }, or if there is no termi- - nating }, this form of escape is not recognized. Instead, the initial - \x will be interpreted as a basic hexadecimal escape, with no following - digits, giving a character whose value is zero. + than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode. That is, + the maximum value in hexadecimal is 7FFFFFFF. Note that this is bigger + than the largest Unicode code point, which is 10FFFF. + + If characters other than hexadecimal digits appear between \x{ and }, + or if there is no terminating }, this form of escape is not recognized. + Instead, the initial \x will be interpreted as a basic hexadecimal + escape, with no following digits, giving a character whose value is + zero. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x. There is no difference in the way they are han- + two syntaxes for \x. There is no difference in the way they are han- dled. For example, \xdc is exactly the same as \x{dc}. - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the sequence \0\x\07 specifies two binary zeros followed by a BEL character - (code value 7). Make sure you supply two digits after the initial zero + (code value 7). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. The handling of a backslash followed by a digit other than 0 is compli- cated. Outside a character class, PCRE reads it and any following dig- - its as a decimal number. If the number is less than 10, or if there + its as a decimal number. If the number is less than 10, or if there have been at least that many previous capturing left parentheses in the - expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion + expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion of parenthesized subpatterns. - Inside a character class, or if the decimal number is greater than 9 - and there have not been that many capturing subpatterns, PCRE re-reads - up to three octal digits following the backslash, ane uses them to gen- - erate a data character. Any subsequent digits stand for themselves. In - non-UTF-8 mode, the value of a character specified in octal must be - less than \400. In UTF-8 mode, values up to \777 are permitted. For + Inside a character class, or if the decimal number is greater than 9 + and there have not been that many capturing subpatterns, PCRE re-reads + up to three octal digits following the backslash, and uses them to gen- + erate a data character. Any subsequent digits stand for themselves. In + non-UTF-8 mode, the value of a character specified in octal must be + less than \400. In UTF-8 mode, values up to \777 are permitted. For example: \040 is another way of writing a space @@ -2713,24 +3216,45 @@ \81 is either a back reference, or a binary zero followed by the two characters "8" and "1" - Note that octal values of 100 or greater must not be introduced by a + Note that octal values of 100 or greater must not be introduced by a leading zero, because no more than three octal digits are ever read. All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character - class, the sequence \b is interpreted as the backspace character (hex - 08), and the sequence \X is interpreted as the character "X". Outside a - character class, these sequences have different meanings (see below). + inside and outside character classes. In addition, inside a character + class, the sequence \b is interpreted as the backspace character (hex + 08), and the sequences \R and \X are interpreted as the characters "R" + and "X", respectively. Outside a character class, these sequences have + different meanings (see below). + + Absolute and relative back references + + The sequence \g followed by an unsigned or a negative number, option- + ally enclosed in braces, is an absolute or relative back reference. A + named back reference can be coded as \g{name}. Back references are dis- + cussed later, following the discussion of parenthesized subpatterns. + + Absolute and relative subroutine calls + + For compatibility with Oniguruma, the non-Perl syntax \g followed by a + name or a number enclosed either in angle brackets or single quotes, is + an alternative syntax for referencing a subpattern as a "subroutine". + Details are discussed later. Note that \g{...} (Perl syntax) and + \g<...> (Oniguruma syntax) are not synonymous. The former is a back + reference; the latter is a subroutine call. Generic character types - The third use of backslash is for specifying generic character types. - The following are always recognized: + Another use of backslash is for specifying generic character types. The + following are always recognized: \d any decimal digit \D any character that is not a decimal digit + \h any horizontal whitespace character + \H any character that is not a horizontal whitespace character \s any whitespace character \S any character that is not a whitespace character + \v any vertical whitespace character + \V any character that is not a vertical whitespace character \w any "word" character \W any "non-word" character @@ -2745,28 +3269,111 @@ For compatibility with Perl, \s does not match the VT character (code 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). (If + characters are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is included in a Perl script, \s may match the VT charac- - ter. In PCRE, it never does.) - - A "word" character is an underscore or any character less than 256 that - is a letter or digit. The definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in the "fr_FR" (French) locale, some character - codes greater than 128 are used for accented letters, and these are - matched by \w. + ter. In PCRE, it never does. In UTF-8 mode, characters with values greater than 128 never match \d, \s, or \w, and always match \D, \S, and \W. This is true even when Uni- - code character property support is available. The use of locales with - Unicode is discouraged. + code character property support is available. These sequences retain + their original meanings from before UTF-8 support was available, mainly + for efficiency reasons. Note that this also affects \b, because it is + defined in terms of \w and \W. + + The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to + the other sequences, these do match certain high-valued codepoints in + UTF-8 mode. The horizontal space characters are: + + U+0009 Horizontal tab + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space + + The vertical space characters are: + + U+000A Linefeed + U+000B Vertical tab + U+000C Formfeed + U+000D Carriage return + U+0085 Next line + U+2028 Line separator + U+2029 Paragraph separator + + A "word" character is an underscore or any character less than 256 that + is a letter or digit. The definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in a French locale such as "fr_FR" in Unix-like + systems, or "french" in Windows, some character codes greater than 128 + are used for accented letters, and these are matched by \w. The use of + locales with Unicode is discouraged. + + Newline sequences + + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 + mode \R is equivalent to the following: + + (?>\r\n|\n|\x0b|\f|\r|\x85) + + This is an example of an "atomic group", details of which are given + below. This particular group matches either the two-character sequence + CR followed by LF, or one of the single characters LF (linefeed, + U+000A), VT (vertical tab, U+000B), FF (formfeed, U+000C), CR (carriage + return, U+000D), or NEL (next line, U+0085). The two-character sequence + is treated as a single unit that cannot be split. + + In UTF-8 mode, two additional characters whose codepoints are greater + than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- + rator, U+2029). Unicode character property support is not needed for + these characters to be recognized. + + It is possible to restrict \R to match only CR, LF, or CRLF (instead of + the complete set of Unicode line endings) by setting the option + PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. + (BSR is an abbrevation for "backslash R".) This can be made the default + when PCRE is built; if this is the case, the other behaviour can be + requested via the PCRE_BSR_UNICODE option. It is also possible to + specify these settings by starting a pattern string with one of the + following sequences: + + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence + + These override the default and the options given to pcre_compile(), but + they can be overridden by options given to pcre_exec(). Note that these + special settings, which are not Perl-compatible, are recognized only at + the very start of a pattern, and that they must be in upper case. If + more than one of them is present, the last one is used. They can be + combined with a change of newline convention, for example, a pattern + can start with: + + (*ANY)(*BSR_ANYCRLF) + + Inside a character class, \R matches the letter "R". Unicode character properties When PCRE is built with Unicode character property support, three addi- - tional escape sequences to match character properties are available - when UTF-8 mode is selected. They are: + tional escape sequences that match characters with specific properties + are available. When not in UTF-8 mode, these sequences are of course + limited to testing characters whose codepoints are less than 256, but + they do work in this mode. The extra escape sequences are: \p{xx} a character with the xx property \P{xx} a character without the xx property @@ -2788,15 +3395,15 @@ Those that are not part of an identified script are lumped together as "Common". The current list of scripts is: - Arabic, Armenian, Bengali, Bopomofo, Braille, Buginese, Buhid, Cana- - dian_Aboriginal, Cherokee, Common, Coptic, Cypriot, Cyrillic, Deseret, - Devanagari, Ethiopic, Georgian, Glagolitic, Gothic, Greek, Gujarati, - Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, Inherited, Kannada, - Katakana, Kharoshthi, Khmer, Lao, Latin, Limbu, Linear_B, Malayalam, - Mongolian, Myanmar, New_Tai_Lue, Ogham, Old_Italic, Old_Persian, Oriya, - Osmanya, Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tag- - banwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, - Ugaritic, Yi. + Arabic, Armenian, Balinese, Bengali, Bopomofo, Braille, Buginese, + Buhid, Canadian_Aboriginal, Cherokee, Common, Coptic, Cuneiform, + Cypriot, Cyrillic, Deseret, Devanagari, Ethiopic, Georgian, Glagolitic, + Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- + gana, Inherited, Kannada, Katakana, Kharoshthi, Khmer, Lao, Latin, + Limbu, Linear_B, Malayalam, Mongolian, Myanmar, New_Tai_Lue, Nko, + Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, Phags_Pa, Phoenician, + Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tagbanwa, + Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Yi. Each character has exactly one general category property, specified by a two-letter abbreviation. For compatibility with Perl, negation can be @@ -2861,6 +3468,12 @@ has the Lu, Ll, or Lt property, in other words, a letter that is not classified as a modifier or "other". + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in UTF-8 strings (see + RFC 3629) and so cannot be tested by PCRE, unless UTF-8 validity check- + ing has been turned off (see the discussion of PCRE_NO_UTF8_CHECK in + the pcreapi page). + The long synonyms for these properties that Perl supports (such as \p{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". @@ -2880,63 +3493,85 @@ That is, it matches a character without the "mark" property, followed by zero or more characters with the "mark" property, and treats the sequence as an atomic group (see below). Characters with the "mark" - property are typically accents that affect the preceding character. + property are typically accents that affect the preceding character. + None of them have codepoints less than 256, so in non-UTF-8 mode \X + matches any one character. Matching characters by Unicode property is not fast, because PCRE has to search a structure that contains data for over fifteen thousand characters. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE. + Resetting the match start + + The escape sequence \K, which is a Perl 5.10 feature, causes any previ- + ously matched characters not to be included in the final matched + sequence. For example, the pattern: + + foo\Kbar + + matches "foobar", but reports that it has matched "bar". This feature + is similar to a lookbehind assertion (described below). However, in + this case, the part of the subject before the real match does not have + to be of fixed length, as lookbehind assertions do. The use of \K does + not interfere with the setting of captured substrings. For example, + when the pattern + + (foo)\Kbar + + matches "foobar", the first substring is still set to "foo". + Simple assertions - The fourth use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. + The final use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. The backslashed assertions are: \b matches at a word boundary \B matches when not at a word boundary - \A matches at start of subject - \Z matches at end of subject or before newline at end - \z matches at end of subject - \G matches at first matching position in subject + \A matches at the start of the subject + \Z matches at the end of the subject + also matches before a newline at the end of the subject + \z matches only at the end of the subject + \G matches at the first matching position in the subject - These assertions may not appear in character classes (but note that \b + These assertions may not appear in character classes (but note that \b has a different meaning, namely the backspace character, inside a char- acter class). - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the string if the first or last character matches \w, respectively. - The \A, \Z, and \z assertions differ from the traditional circumflex + The \A, \Z, and \z assertions differ from the traditional circumflex and dollar (described in the next section) in that they only ever match - at the very start and end of the subject string, whatever options are - set. Thus, they are independent of multiline mode. These three asser- + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which - affect only the behaviour of the circumflex and dollar metacharacters. - However, if the startoffset argument of pcre_exec() is non-zero, indi- + affect only the behaviour of the circumflex and dollar metacharacters. + However, if the startoffset argument of pcre_exec() is non-zero, indi- cating that matching is to start at a point other than the beginning of - the subject, \A can never match. The difference between \Z and \z is + the subject, \A can never match. The difference between \Z and \z is that \Z matches before a newline at the end of the string as well as at the very end, whereas \z matches only at the end. - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre_exec(). It differs from \A when the value of startoffset is - non-zero. By calling pcre_exec() multiple times with appropriate argu- + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre_exec(). It differs from \A when the value of startoffset is + non-zero. By calling pcre_exec() multiple times with appropriate argu- ments, you can mimic Perl's /g option, and it is in this kind of imple- mentation where \G can be useful. - Note, however, that PCRE's interpretation of \G, as the start of the + Note, however, that PCRE's interpretation of \G, as the start of the current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE does just one match + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE does just one match at a time, it cannot reproduce this behaviour. - If all the alternatives of a pattern begin with \G, the expression is + If all the alternatives of a pattern begin with \G, the expression is anchored to the starting match position, and the "anchored" flag is set in the compiled regular expression. @@ -2944,69 +3579,72 @@ CIRCUMFLEX AND DOLLAR Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre_exec() is non-zero, circumflex can never match if the + PCRE_MULTILINE option is unset. Inside a character class, circumflex has an entirely different meaning (see below). - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other constructs that can cause a pattern to be anchored.) - A dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately + A dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately before a newline at the end of the string (by default). Dollar need not - be the last character of the pattern if a number of alternatives are - involved, but it should be the last item in any branch in which it + be the last character of the pattern if a number of alternatives are + involved, but it should be the last item in any branch in which it appears. Dollar has no special meaning in a character class. - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at + The meaning of dollar can be changed so that it matches only at the + very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This does not affect the \Z assertion. The meanings of the circumflex and dollar characters are changed if the - PCRE_MULTILINE option is set. When this is the case, a circumflex - matches immediately after internal newlines as well as at the start of - the subject string. It does not match after a newline that ends the - string. A dollar matches before any newlines in the string, as well as - at the very end, when PCRE_MULTILINE is set. When newline is specified - as the two-character sequence CRLF, isolated CR and LF characters do + PCRE_MULTILINE option is set. When this is the case, a circumflex + matches immediately after internal newlines as well as at the start of + the subject string. It does not match after a newline that ends the + string. A dollar matches before any newlines in the string, as well as + at the very end, when PCRE_MULTILINE is set. When newline is specified + as the two-character sequence CRLF, isolated CR and LF characters do not indicate newlines. - For example, the pattern /^abc$/ matches the subject string "def\nabc" - (where \n represents a newline) in multiline mode, but not otherwise. - Consequently, patterns that are anchored in single line mode because - all branches start with ^ are not anchored in multiline mode, and a - match for circumflex is possible when the startoffset argument of - pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if + For example, the pattern /^abc$/ matches the subject string "def\nabc" + (where \n represents a newline) in multiline mode, but not otherwise. + Consequently, patterns that are anchored in single line mode because + all branches start with ^ are not anchored in multiline mode, and a + match for circumflex is possible when the startoffset argument of + pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. - Note that the sequences \A, \Z, and \z can be used to match the start - and end of the subject in both modes, and if all branches of a pattern - start with \A it is always anchored, whether or not PCRE_MULTILINE is + Note that the sequences \A, \Z, and \z can be used to match the start + and end of the subject in both modes, and if all branches of a pattern + start with \A it is always anchored, whether or not PCRE_MULTILINE is set. FULL STOP (PERIOD, DOT) Outside a character class, a dot in the pattern matches any one charac- - ter in the subject string except (by default) a character that signi- - fies the end of a line. In UTF-8 mode, the matched character may be - more than one byte long. When a line ending is defined as a single - character (CR or LF), dot never matches that character; when the two- - character sequence CRLF is used, dot does not match CR if it is immedi- - ately followed by LF, but otherwise it matches all characters (includ- - ing isolated CRs and LFs). + ter in the subject string except (by default) a character that signi- + fies the end of a line. In UTF-8 mode, the matched character may be + more than one byte long. + + When a line ending is defined as a single character, dot never matches + that character; when the two-character sequence CRLF is used, dot does + not match CR if it is immediately followed by LF, but otherwise it + matches all characters (including isolated CRs and LFs). When any Uni- + code line endings are being recognized, dot does not match CR or LF or + any of the other line ending characters. The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL option is set, a dot matches any one character, without - exception. If newline is defined as the two-character sequence CRLF, it - takes two dots to match it. + exception. If the two-character sequence CRLF is present in the subject + string, it takes two dots to match it. The handling of dot is entirely independent of the handling of circum- flex and dollar, the only relationship being that they both involve @@ -3016,14 +3654,15 @@ MATCHING A SINGLE BYTE Outside a character class, the escape sequence \C matches any one byte, - both in and out of UTF-8 mode. Unlike a dot, it always matches CR and - LF. The feature is provided in Perl in order to match individual bytes - in UTF-8 mode. Because it breaks up UTF-8 characters into individual - bytes, what remains in the string may be a malformed UTF-8 string. For - this reason, the \C escape sequence is best avoided. + both in and out of UTF-8 mode. Unlike a dot, it always matches any + line-ending characters. The feature is provided in Perl in order to + match individual bytes in UTF-8 mode. Because it breaks up UTF-8 char- + acters into individual bytes, what remains in the string may be a mal- + formed UTF-8 string. For this reason, the \C escape sequence is best + avoided. - PCRE does not allow \C to appear in lookbehind assertions (described - below), because in UTF-8 mode this would make it impossible to calcu- + PCRE does not allow \C to appear in lookbehind assertions (described + below), because in UTF-8 mode this would make it impossible to calcu- late the length of the lookbehind. @@ -3032,96 +3671,96 @@ An opening square bracket introduces a character class, terminated by a closing square bracket. A closing square bracket on its own is not spe- cial. If a closing square bracket is required as a member of the class, - it should be the first data character in the class (after an initial + it should be the first data character in the class (after an initial circumflex, if present) or escaped with a backslash. - A character class matches a single character in the subject. In UTF-8 - mode, the character may occupy more than one byte. A matched character + A character class matches a single character in the subject. In UTF-8 + mode, the character may occupy more than one byte. A matched character must be in the set of characters defined by the class, unless the first - character in the class definition is a circumflex, in which case the - subject character must not be in the set defined by the class. If a - circumflex is actually required as a member of the class, ensure it is + character in the class definition is a circumflex, in which case the + subject character must not be in the set defined by the class. If a + circumflex is actually required as a member of the class, ensure it is not the first character, or escape it with a backslash. - For example, the character class [aeiou] matches any lower case vowel, - while [^aeiou] matches any character that is not a lower case vowel. + For example, the character class [aeiou] matches any lower case vowel, + while [^aeiou] matches any character that is not a lower case vowel. Note that a circumflex is just a convenient notation for specifying the - characters that are in the class by enumerating those that are not. A - class that starts with a circumflex is not an assertion: it still con- - sumes a character from the subject string, and therefore it fails if + characters that are in the class by enumerating those that are not. A + class that starts with a circumflex is not an assertion: it still con- + sumes a character from the subject string, and therefore it fails if the current pointer is at the end of the string. - In UTF-8 mode, characters with values greater than 255 can be included - in a class as a literal string of bytes, or by using the \x{ escaping + In UTF-8 mode, characters with values greater than 255 can be included + in a class as a literal string of bytes, or by using the \x{ escaping mechanism. - When caseless matching is set, any letters in a class represent both - their upper case and lower case versions, so for example, a caseless - [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not - match "A", whereas a caseful version would. In UTF-8 mode, PCRE always - understands the concept of case for characters whose values are less - than 128, so caseless matching is always possible. For characters with - higher values, the concept of case is supported if PCRE is compiled - with Unicode property support, but not otherwise. If you want to use - caseless matching for characters 128 and above, you must ensure that - PCRE is compiled with Unicode property support as well as with UTF-8 + When caseless matching is set, any letters in a class represent both + their upper case and lower case versions, so for example, a caseless + [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not + match "A", whereas a caseful version would. In UTF-8 mode, PCRE always + understands the concept of case for characters whose values are less + than 128, so caseless matching is always possible. For characters with + higher values, the concept of case is supported if PCRE is compiled + with Unicode property support, but not otherwise. If you want to use + caseless matching for characters 128 and above, you must ensure that + PCRE is compiled with Unicode property support as well as with UTF-8 support. - Characters that might indicate line breaks (CR and LF) are never - treated in any special way when matching character classes, whatever - line-ending sequence is in use, and whatever setting of the PCRE_DOTALL - and PCRE_MULTILINE options is used. A class such as [^a] always matches - one of these characters. - - The minus (hyphen) character can be used to specify a range of charac- - ters in a character class. For example, [d-m] matches any letter - between d and m, inclusive. If a minus character is required in a - class, it must be escaped with a backslash or appear in a position - where it cannot be interpreted as indicating a range, typically as the + Characters that might indicate line breaks are never treated in any + special way when matching character classes, whatever line-ending + sequence is in use, and whatever setting of the PCRE_DOTALL and + PCRE_MULTILINE options is used. A class such as [^a] always matches one + of these characters. + + The minus (hyphen) character can be used to specify a range of charac- + ters in a character class. For example, [d-m] matches any letter + between d and m, inclusive. If a minus character is required in a + class, it must be escaped with a backslash or appear in a position + where it cannot be interpreted as indicating a range, typically as the first or last character in the class. It is not possible to have the literal character "]" as the end charac- - ter of a range. A pattern such as [W-]46] is interpreted as a class of - two characters ("W" and "-") followed by a literal string "46]", so it - would match "W46]" or "-46]". However, if the "]" is escaped with a - backslash it is interpreted as the end of range, so [W-\]46] is inter- - preted as a class containing a range followed by two other characters. - The octal or hexadecimal representation of "]" can also be used to end + ter of a range. A pattern such as [W-]46] is interpreted as a class of + two characters ("W" and "-") followed by a literal string "46]", so it + would match "W46]" or "-46]". However, if the "]" is escaped with a + backslash it is interpreted as the end of range, so [W-\]46] is inter- + preted as a class containing a range followed by two other characters. + The octal or hexadecimal representation of "]" can also be used to end a range. - Ranges operate in the collating sequence of character values. They can - also be used for characters specified numerically, for example - [\000-\037]. In UTF-8 mode, ranges can include characters whose values + Ranges operate in the collating sequence of character values. They can + also be used for characters specified numerically, for example + [\000-\037]. In UTF-8 mode, ranges can include characters whose values are greater than 255, for example [\x{100}-\x{2ff}]. If a range that includes letters is used when caseless matching is set, it matches the letters in either case. For example, [W-c] is equivalent - to [][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if - character tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches - accented E characters in both cases. In UTF-8 mode, PCRE supports the - concept of case for characters with values greater than 128 only when + to [][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if + character tables for a French locale are in use, [\xc8-\xcb] matches + accented E characters in both cases. In UTF-8 mode, PCRE supports the + concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. - The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear - in a character class, and add the characters that they match to the + The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear + in a character class, and add the characters that they match to the class. For example, [\dABCDEF] matches any hexadecimal digit. A circum- - flex can conveniently be used with the upper case character types to - specify a more restricted set of characters than the matching lower - case type. For example, the class [^\W_] matches any letter or digit, + flex can conveniently be used with the upper case character types to + specify a more restricted set of characters than the matching lower + case type. For example, the class [^\W_] matches any letter or digit, but not underscore. - The only metacharacters that are recognized in character classes are - backslash, hyphen (only where it can be interpreted as specifying a - range), circumflex (only at the start), opening square bracket (only - when it can be interpreted as introducing a POSIX class name - see the - next section), and the terminating closing square bracket. However, + The only metacharacters that are recognized in character classes are + backslash, hyphen (only where it can be interpreted as specifying a + range), circumflex (only at the start), opening square bracket (only + when it can be interpreted as introducing a POSIX class name - see the + next section), and the terminating closing square bracket. However, escaping other non-alphanumeric characters does no harm. POSIX CHARACTER CLASSES Perl supports the POSIX notation for character classes. This uses names - enclosed by [: and :] within the enclosing square brackets. PCRE also + enclosed by [: and :] within the enclosing square brackets. PCRE also supports this notation. For example, [01[:alpha:]%] @@ -3144,18 +3783,18 @@ word "word" characters (same as \w) xdigit hexadecimal digits - The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), - and space (32). Notice that this list includes the VT character (code + The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), + and space (32). Notice that this list includes the VT character (code 11). This makes "space" different to \s, which does not include VT (for Perl compatibility). - The name "word" is a Perl extension, and "blank" is a GNU extension - from Perl 5.8. Another Perl extension is negation, which is indicated + The name "word" is a Perl extension, and "blank" is a GNU extension + from Perl 5.8. Another Perl extension is negation, which is indicated by a ^ character after the colon. For example, [12[:^digit:]] - matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the + matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not supported, and an error is given if they are encountered. @@ -3175,15 +3814,15 @@ string). The matching process tries each alternative in turn, from left to right, and the first one that succeeds is used. If the alternatives are within a subpattern (defined below), "succeeds" means matching the - rest of the main pattern as well as the alternative in the subpattern. + rest of the main pattern as well as the alternative in the subpattern. INTERNAL OPTION SETTING - The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and - PCRE_EXTENDED options can be changed from within the pattern by a - sequence of Perl option letters enclosed between "(?" and ")". The - option letters are + The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and + PCRE_EXTENDED options (which are Perl-compatible) can be changed from + within the pattern by a sequence of Perl option letters enclosed + between "(?" and ")". The option letters are i for PCRE_CASELESS m for PCRE_MULTILINE @@ -3192,19 +3831,24 @@ For example, (?im) sets caseless, multiline matching. It is also possi- ble to unset these options by preceding the letter with a hyphen, and a - combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- - LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, - is also permitted. If a letter appears both before and after the + combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- + LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, + is also permitted. If a letter appears both before and after the hyphen, the option is unset. - When an option change occurs at top level (that is, not inside subpat- - tern parentheses), the change applies to the remainder of the pattern - that follows. If the change is placed right at the start of a pattern, - PCRE extracts it into the global options (and it will therefore show up - in data extracted by the pcre_fullinfo() function). + The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA + can be changed in the same way as the Perl-compatible options by using + the characters J, U and X respectively. - An option change within a subpattern affects only that part of the cur- - rent pattern that follows it, so + When one of these option changes occurs at top level (that is, not + inside subpattern parentheses), the change applies to the remainder of + the pattern that follows. If the change is placed right at the start of + a pattern, PCRE extracts it into the global options (and it will there- + fore show up in data extracted by the pcre_fullinfo() function). + + An option change within a subpattern (see below for a description of + subpatterns) affects only that part of the current pattern that follows + it, so (a(?i)b)c @@ -3221,9 +3865,13 @@ the effects of option settings happen at compile time. There would be some very weird behaviour otherwise. - The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA - can be changed in the same way as the Perl-compatible options by using - the characters J, U and X respectively. + Note: There are other PCRE-specific options that can be set by the + application when the compile or match functions are called. In some + cases the pattern can contain special leading sequences such as (*CRLF) + to override what the application has set or what has been defaulted. + Details are given in the section entitled "Newline sequences" above. + There is also the (*UTF8) leading sequence that can be used to set + UTF-8 mode; this is equivalent to setting the PCRE_UTF8 option. SUBPATTERNS @@ -3236,7 +3884,7 @@ cat(aract|erpillar|) matches one of the words "cat", "cataract", or "caterpillar". Without - the parentheses, it would match "cataract", "erpillar" or the empty + the parentheses, it would match "cataract", "erpillar" or an empty string. 2. It sets up the subpattern as a capturing subpattern. This means @@ -3265,9 +3913,7 @@ the ((?:red|white) (king|queen)) the captured substrings are "white queen" and "queen", and are numbered - 1 and 2. The maximum number of capturing subpatterns is 65535, and the - maximum depth of nesting of all subpatterns, both capturing and non- - capturing, is 200. + 1 and 2. The maximum number of capturing subpatterns is 65535. As a convenient shorthand, if any option settings are required at the start of a non-capturing subpattern, the option letters may appear @@ -3283,73 +3929,118 @@ "Saturday". +DUPLICATE SUBPATTERN NUMBERS + + Perl 5.10 introduced a feature whereby each alternative in a subpattern + uses the same numbers for its capturing parentheses. Such a subpattern + starts with (?| and is itself a non-capturing subpattern. For example, + consider this pattern: + + (?|(Sat)ur|(Sun))day + + Because the two alternatives are inside a (?| group, both sets of cap- + turing parentheses are numbered one. Thus, when the pattern matches, + you can look at captured substring number one, whichever alternative + matched. This construct is useful when you want to capture part, but + not all, of one of a number of alternatives. Inside a (?| group, paren- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing buffers that follow the sub- + pattern start after the highest number used in any branch. The follow- + ing example is taken from the Perl documentation. The numbers under- + neath show in which buffer the captured content will be stored. + + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 + + A backreference or a recursive call to a numbered subpattern always + refers to the first one in the pattern with the given number. + + An alternative approach to using this "branch reset" feature is to use + duplicate named subpatterns, as described in the next section. + + NAMED SUBPATTERNS Identifying capturing parentheses by number is simple, but it can be very hard to keep track of the numbers in complicated regular expres- sions. Furthermore, if an expression is modified, the numbers may change. To help with this difficulty, PCRE supports the naming of sub- - patterns, something that Perl does not provide. The Python syntax - (?P<name>...) is used. References to capturing parentheses from other - parts of the pattern, such as backreferences, recursion, and condi- - tions, can be made by name as well as by number. + patterns. This feature was not added to Perl until release 5.10. Python + had the feature earlier, and PCRE introduced it at release 4.0, using + the Python syntax. PCRE now supports both the Perl and the Python syn- + tax. + + In PCRE, a subpattern can be named in one of three ways: (?<name>...) + or (?'name'...) as in Perl, or (?P<name>...) as in Python. References + to capturing parentheses from other parts of the pattern, such as back- + references, recursion, and conditions, can be made by name as well as + by number. Names consist of up to 32 alphanumeric characters and underscores. Named capturing parentheses are still allocated numbers as well as - names. The PCRE API provides function calls for extracting the name-to- - number translation table from a compiled pattern. There is also a con- - venience function for extracting a captured substring by name. + names, exactly as if the names were not present. The PCRE API provides + function calls for extracting the name-to-number translation table from + a compiled pattern. There is also a convenience function for extracting + a captured substring by name. - By default, a name must be unique within a pattern, but it is possible + By default, a name must be unique within a pattern, but it is possible to relax this constraint by setting the PCRE_DUPNAMES option at compile - time. This can be useful for patterns where only one instance of the - named parentheses can match. Suppose you want to match the name of a - weekday, either as a 3-letter abbreviation or as the full name, and in + time. This can be useful for patterns where only one instance of the + named parentheses can match. Suppose you want to match the name of a + weekday, either as a 3-letter abbreviation or as the full name, and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: - (?P<DN>Mon|Fri|Sun)(?:day)?| - (?P<DN>Tue)(?:sday)?| - (?P<DN>Wed)(?:nesday)?| - (?P<DN>Thu)(?:rsday)?| - (?P<DN>Sat)(?:urday)? - - There are five capturing substrings, but only one is ever set after a - match. The convenience function for extracting the data by name - returns the substring for the first, and in this example, the only, - subpattern of that name that matched. This saves searching to find - which numbered subpattern it was. If you make a reference to a non- - unique named subpattern from elsewhere in the pattern, the one that - corresponds to the lowest number is used. For further details of the - interfaces for handling named subpatterns, see the pcreapi documenta- - tion. + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? + + There are five capturing substrings, but only one is ever set after a + match. (An alternative way of solving this problem is to use a "branch + reset" subpattern, as described in the previous section.) + + The convenience function for extracting the data by name returns the + substring for the first (and in this example, the only) subpattern of + that name that matched. This saves searching to find which numbered + subpattern it was. If you make a reference to a non-unique named sub- + pattern from elsewhere in the pattern, the one that corresponds to the + lowest number is used. For further details of the interfaces for han- + dling named subpatterns, see the pcreapi documentation. + + Warning: You cannot use different names to distinguish between two sub- + patterns with the same number (see the previous section) because PCRE + uses only the numbers when matching. REPETITION - Repetition is specified by quantifiers, which can follow any of the + Repetition is specified by quantifiers, which can follow any of the following items: a literal data character - the . metacharacter + the dot metacharacter the \C escape sequence the \X escape sequence (in UTF-8 mode with Unicode properties) + the \R escape sequence an escape such as \d that matches a single character a character class a back reference (see next section) a parenthesized subpattern (unless it is an assertion) - The general repetition quantifier specifies a minimum and maximum num- - ber of permitted matches, by giving the two numbers in curly brackets - (braces), separated by a comma. The numbers must be less than 65536, + The general repetition quantifier specifies a minimum and maximum num- + ber of permitted matches, by giving the two numbers in curly brackets + (braces), separated by a comma. The numbers must be less than 65536, and the first must be less than or equal to the second. For example: z{2,4} - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required matches. Thus [aeiou]{3,} @@ -3358,9 +4049,9 @@ \d{8} - matches exactly 8 digits. An opening curly bracket that appears in a - position where a quantifier is not allowed, or one that does not match - the syntax of a quantifier, is taken as a literal character. For exam- + matches exactly 8 digits. An opening curly bracket that appears in a + position where a quantifier is not allowed, or one that does not match + the syntax of a quantifier, is taken as a literal character. For exam- ple, {,6} is not a quantifier, but a literal string of four characters. In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to @@ -3371,33 +4062,36 @@ may be of different lengths). The quantifier {0} is permitted, causing the expression to behave as if - the previous item and the quantifier were not present. + the previous item and the quantifier were not present. This may be use- + ful for subpatterns that are referenced as subroutines from elsewhere + in the pattern. Items other than subpatterns that have a {0} quantifier + are omitted from the compiled pattern. - For convenience (and historical compatibility) the three most common - quantifiers have single-character abbreviations: + For convenience, the three most common quantifiers have single-charac- + ter abbreviations: * is equivalent to {0,} + is equivalent to {1,} ? is equivalent to {0,1} - It is possible to construct infinite loops by following a subpattern + It is possible to construct infinite loops by following a subpattern that can match no characters with a quantifier that has no upper limit, for example: (a?)* Earlier versions of Perl and PCRE used to give an error at compile time - for such patterns. However, because there are cases where this can be - useful, such patterns are now accepted, but if any repetition of the - subpattern does in fact match no characters, the loop is forcibly bro- + for such patterns. However, because there are cases where this can be + useful, such patterns are now accepted, but if any repetition of the + subpattern does in fact match no characters, the loop is forcibly bro- ken. - By default, the quantifiers are "greedy", that is, they match as much - as possible (up to the maximum number of permitted times), without - causing the rest of the pattern to fail. The classic example of where + By default, the quantifiers are "greedy", that is, they match as much + as possible (up to the maximum number of permitted times), without + causing the rest of the pattern to fail. The classic example of where this gives problems is in trying to match comments in C programs. These - appear between /* and */ and within the comment, individual * and / - characters may appear. An attempt to match C comments by applying the + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the pattern /\*.*\*/ @@ -3406,19 +4100,19 @@ /* first comment */ not comment /* second comment */ - fails, because it matches the entire string owing to the greediness of + fails, because it matches the entire string owing to the greediness of the .* item. - However, if a quantifier is followed by a question mark, it ceases to + However, if a quantifier is followed by a question mark, it ceases to be greedy, and instead matches the minimum number of times possible, so the pattern /\*.*?\*/ - does the right thing with the C comments. The meaning of the various - quantifiers is not otherwise changed, just the preferred number of - matches. Do not confuse this use of question mark with its use as a - quantifier in its own right. Because it has two uses, it can sometimes + does the right thing with the C comments. The meaning of the various + quantifiers is not otherwise changed, just the preferred number of + matches. Do not confuse this use of question mark with its use as a + quantifier in its own right. Because it has two uses, it can sometimes appear doubled, as in \d??\d @@ -3426,22 +4120,23 @@ which matches one digit by preference, but can match two if that is the only way the rest of the pattern matches. - If the PCRE_UNGREEDY option is set (an option which is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other + If the PCRE_UNGREEDY option is set (an option that is not available in + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. - When a parenthesized subpattern is quantified with a minimum repeat - count that is greater than 1 or with a limited maximum, more memory is - required for the compiled pattern, in proportion to the size of the + When a parenthesized subpattern is quantified with a minimum repeat + count that is greater than 1 or with a limited maximum, more memory is + required for the compiled pattern, in proportion to the size of the minimum or maximum. If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- - alent to Perl's /s) is set, thus allowing the . to match newlines, the - pattern is implicitly anchored, because whatever follows will be tried - against every character position in the subject string, so there is no - point in retrying the overall match at any position after the first. - PCRE normally treats such a pattern as though it were preceded by \A. + alent to Perl's /s) is set, thus allowing the dot to match newlines, + the pattern is implicitly anchored, because whatever follows will be + tried against every character position in the subject string, so there + is no point in retrying the overall match at any position after the + first. PCRE normally treats such a pattern as though it were preceded + by \A. In cases where it is known that the subject string contains no new- lines, it is worth setting PCRE_DOTALL in order to obtain this opti- @@ -3449,8 +4144,8 @@ However, there is one situation where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a - backreference elsewhere in the pattern, a match at the start may fail, - and a later one succeed. Consider, for example: + backreference elsewhere in the pattern, a match at the start may fail + where a later one succeeds. Consider, for example: (.*)abc\1 @@ -3474,29 +4169,29 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - With both maximizing and minimizing repetition, failure of what follows - normally causes the repeated item to be re-evaluated to see if a dif- - ferent number of repeats allows the rest of the pattern to match. Some- - times it is useful to prevent this, either to change the nature of the - match, or to cause it fail earlier than it otherwise might, when the - author of the pattern knows there is no point in carrying on. + With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") + repetition, failure of what follows normally causes the repeated item + to be re-evaluated to see if a different number of repeats allows the + rest of the pattern to match. Sometimes it is useful to prevent this, + either to change the nature of the match, or to cause it fail earlier + than it otherwise might, when the author of the pattern knows there is + no point in carrying on. - Consider, for example, the pattern \d+foo when applied to the subject + Consider, for example, the pattern \d+foo when applied to the subject line 123456bar After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides - the means for specifying that once a subpattern has matched, it is not + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + the means for specifying that once a subpattern has matched, it is not to be re-evaluated in this way. - If we use atomic grouping for the previous example, the matcher would - give up immediately on failing to match "foo" the first time. The nota- - tion is a kind of special parenthesis, starting with (?> as in this - example: + If we use atomic grouping for the previous example, the matcher gives + up immediately on failing to match "foo" the first time. The notation + is a kind of special parenthesis, starting with (?> as in this example: (?>\d+)foo @@ -3525,16 +4220,28 @@ \d++foo - Possessive quantifiers are always greedy; the setting of the + Note that a possessive quantifier can be used with an entire group, for + example: + + (abc|xyz){2,3}+ + + Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY option is ignored. They are a convenient notation for the - simpler forms of atomic group. However, there is no difference in the - meaning or processing of a possessive quantifier and the equivalent - atomic group. - - The possessive quantifier syntax is an extension to the Perl syntax. - Jeffrey Friedl originated the idea (and the name) in the first edition - of his book. Mike McCloskey liked it, so implemented it when he built - Sun's Java package, and PCRE copied it from there. + simpler forms of atomic group. However, there is no difference in the + meaning of a possessive quantifier and the equivalent atomic group, + though there may be a performance difference; possessive quantifiers + should be slightly faster. + + The possessive quantifier syntax is an extension to the Perl 5.8 syn- + tax. Jeffrey Friedl originated the idea (and the name) in the first + edition of his book. Mike McCloskey liked it, so implemented it when he + built Sun's Java package, and PCRE copied it from there. It ultimately + found its way into Perl at release 5.10. + + PCRE has an optimization that automatically "possessifies" certain sim- + ple pattern constructs. For example, the sequence A+B is treated as + A++B because there is no point in backtracking into a sequence of A's + when B must follow. When a pattern contains an unlimited repeat inside a subpattern that can itself be repeated an unlimited number of times, the use of an @@ -3561,30 +4268,55 @@ ((?>\D+)|<\d+>)*[!?] - sequences of non-digits cannot be broken, and failure happens quickly. + sequences of non-digits cannot be broken, and failure happens quickly. BACK REFERENCES Outside a character class, a backslash followed by a digit greater than 0 (and possibly further digits) is a back reference to a capturing sub- - pattern earlier (that is, to its left) in the pattern, provided there + pattern earlier (that is, to its left) in the pattern, provided there have been that many previous capturing left parentheses. However, if the decimal number following the backslash is less than 10, - it is always taken as a back reference, and causes an error only if - there are not that many capturing left parentheses in the entire pat- - tern. In other words, the parentheses that are referenced need not be - to the left of the reference for numbers less than 10. A "forward back - reference" of this type can make sense when a repetition is involved - and the subpattern to the right has participated in an earlier itera- + it is always taken as a back reference, and causes an error only if + there are not that many capturing left parentheses in the entire pat- + tern. In other words, the parentheses that are referenced need not be + to the left of the reference for numbers less than 10. A "forward back + reference" of this type can make sense when a repetition is involved + and the subpattern to the right has participated in an earlier itera- tion. - It is not possible to have a numerical "forward back reference" to sub- - pattern whose number is 10 or more. However, a back reference to any - subpattern is possible using named parentheses (see below). See also - the subsection entitled "Non-printing characters" above for further - details of the handling of digits following a backslash. + It is not possible to have a numerical "forward back reference" to a + subpattern whose number is 10 or more using this syntax because a + sequence such as \50 is interpreted as a character defined in octal. + See the subsection entitled "Non-printing characters" above for further + details of the handling of digits following a backslash. There is no + such problem when named parentheses are used. A back reference to any + subpattern is possible using named parentheses (see below). + + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence, which is a fea- + ture introduced in Perl 5.10. This escape must be followed by an + unsigned number or a negative number, optionally enclosed in braces. + These examples are all identical: + + (ring), \1 + (ring), \g1 + (ring), \g{1} + + An unsigned number specifies an absolute reference without the ambigu- + ity that is present in the older syntax. It is also useful when literal + digits follow the reference. A negative number is a relative reference. + Consider this example: + + (abc(def)ghi)\g{-1} + + The sequence \g{-1} is a reference to the most recently started captur- + ing subpattern before \g, that is, is it equivalent to \2. Similarly, + \g{-2} would be equivalent to \1. The use of relative references can be + helpful in long patterns, and also in patterns that are created by + joining together fragments that contain references within themselves. A back reference matches whatever actually matched the capturing sub- pattern in the current subject string, rather than anything matching @@ -3603,10 +4335,17 @@ matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capturing subpattern is matched caselessly. - Back references to named subpatterns use the Python syntax (?P=name). - We could rewrite the above example as follows: + There are several different ways of writing back references to named + subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or + \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's + unified back reference syntax, in which \g can be used for both numeric + and named references, is also supported. We could rewrite the above + example in any of the following ways: + (?<p1>(?i)rah)\s+\k<p1> + (?'p1'(?i)rah)\s+\k{p1} (?P<p1>(?i)rah)\s+(?P=p1) + (?<p1>(?i)rah)\s+\g{p1} A subpattern that is referenced by name may appear in the pattern before or after the reference. @@ -3721,19 +4460,23 @@ (?<=abc|abde) + In some cases, the Perl 5.10 escape sequence \K (see above) can be used + instead of a lookbehind assertion; this is not restricted to a fixed- + length. + The implementation of lookbehind assertions is, for each alternative, - to temporarily move the current position back by the fixed width and + to temporarily move the current position back by the fixed length and then try to match. If there are insufficient characters before the cur- - rent position, the match is deemed to fail. + rent position, the assertion fails. PCRE does not allow the \C escape (which matches a single byte in UTF-8 mode) to appear in lookbehind assertions, because it makes it impossi- - ble to calculate the length of the lookbehind. The \X escape, which can - match different numbers of bytes, is also not permitted. + ble to calculate the length of the lookbehind. The \X and \R escapes, + which can match different numbers of bytes, are also not permitted. - Atomic groups can be used in conjunction with lookbehind assertions to - specify efficient matching at the end of the subject string. Consider a - simple pattern such as + Possessive quantifiers can be used in conjunction with lookbehind + assertions to specify efficient matching at the end of the subject + string. Consider a simple pattern such as abcd$ @@ -3750,13 +4493,9 @@ again the search for "a" covers the entire string, from right to left, so we are no better off. However, if the pattern is written as - ^(?>.*)(?<=abcd) - - or, equivalently, using the possessive quantifier syntax, - ^.*+(?<=abcd) - there can be no backtracking for the .* item; it can match only the + there can be no backtracking for the .*+ item; it can match only the entire string. The subsequent lookbehind assertion does a single test on the last four characters. If it fails, the match fails immediately. For long strings, this approach makes a significant difference to the @@ -3811,15 +4550,19 @@ no-pattern (if present) is used. If there are more than two alterna- tives in the subpattern, a compile-time error occurs. - There are three kinds of condition. If the text between the parentheses - consists of a sequence of digits, or a sequence of alphanumeric charac- - ters and underscores, the condition is satisfied if the capturing sub- - pattern of that number or name has previously matched. There is a pos- - sible ambiguity here, because subpattern names may consist entirely of - digits. PCRE looks first for a named subpattern; if it cannot find one - and the text consists entirely of digits, it looks for a subpattern of - that number, which must be greater than zero. Using subpattern names - that consist entirely of digits is not recommended. + There are four kinds of condition: references to subpatterns, refer- + ences to recursion, a pseudo-condition called DEFINE, and assertions. + + Checking for a used subpattern by number + + If the text between the parentheses consists of a sequence of digits, + the condition is true if the capturing subpattern of that number has + previously matched. An alternative notation is to precede the digits + with a plus or minus sign. In this case, the subpattern number is rela- + tive rather than absolute. The most recently opened parentheses can be + referenced by (?(-1), the next most recent by (?(-2), and so on. In + looping constructs it can also make sense to refer to subsequent groups + with constructs such as (?(+2). Consider the following pattern, which contains non-significant white space to make it more readable (assume the PCRE_EXTENDED option) and to @@ -3836,18 +4579,76 @@ tern is executed and a closing parenthesis is required. Otherwise, since no-pattern is not present, the subpattern matches nothing. In other words, this pattern matches a sequence of non-parentheses, - optionally enclosed in parentheses. Rewriting it to use a named subpat- - tern gives this: + optionally enclosed in parentheses. - (?P<OPEN> \( )? [^()]+ (?(OPEN) \) ) + If you were embedding this pattern in a larger one, you could use a + relative reference: + + ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... + + This makes the fragment independent of the parentheses in the larger + pattern. + + Checking for a used subpattern by name + + Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a + used subpattern by name. For compatibility with earlier versions of + PCRE, which had this facility before Perl, the syntax (?(name)...) is + also recognized. However, there is a possible ambiguity with this syn- + tax, because subpattern names may consist entirely of digits. PCRE + looks first for a named subpattern; if it cannot find one and the name + consists entirely of digits, PCRE looks for a subpattern of that num- + ber, which must be greater than zero. Using subpattern names that con- + sist entirely of digits is not recommended. + + Rewriting the above example to use a named subpattern gives this: + + (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) + + + Checking for pattern recursion If the condition is the string (R), and there is no subpattern with the - name R, the condition is satisfied if a recursive call to the pattern - or subpattern has been made. At "top level", the condition is false. - This is a PCRE extension. Recursive patterns are described in the next - section. + name R, the condition is true if a recursive call to the whole pattern + or any subpattern has been made. If digits or a name preceded by amper- + sand follow the letter R, for example: + + (?(R3)...) or (?(R&name)...) + + the condition is true if the most recent recursion is into the subpat- + tern whose number or name is given. This condition does not check the + entire recursion stack. + + At "top level", all these recursion test conditions are false. Recur- + sive patterns are described below. + + Defining subpatterns for use by reference only + + If the condition is the string (DEFINE), and there is no subpattern + with the name DEFINE, the condition is always false. In this case, + there may be only one alternative in the subpattern. It is always + skipped if control reaches this point in the pattern; the idea of + DEFINE is that it can be used to define "subroutines" that can be ref- + erenced from elsewhere. (The use of "subroutines" is described below.) + For example, a pattern to match an IPv4 address could be written like + this (ignore whitespace and line breaks): + + (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) + \b (?&byte) (\.(?&byte)){3} \b + + The first part of the pattern is a DEFINE group inside which a another + group named "byte" is defined. This matches an individual component of + an IPv4 address (a number less than 256). When matching takes place, + this part of the pattern is skipped because DEFINE acts like a false + condition. + + The rest of the pattern uses references to the named group to match the + four dot-separated components of an IPv4 address, insisting on a word + boundary at each end. + + Assertion conditions - If the condition is not a sequence of digits or (R), it must be an + If the condition is not in any of the above formats, it must be an assertion. This may be a positive or negative lookahead or lookbehind assertion. Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: @@ -3882,111 +4683,139 @@ unlimited nested parentheses. Without the use of recursion, the best that can be done is to use a pattern that matches up to some fixed depth of nesting. It is not possible to handle an arbitrary nesting - depth. Perl provides a facility that allows regular expressions to - recurse (amongst other things). It does this by interpolating Perl code - in the expression at run time, and the code can refer to the expression - itself. A Perl pattern to solve the parentheses problem can be created - like this: + depth. + + For some time, Perl has provided a facility that allows regular expres- + sions to recurse (amongst other things). It does this by interpolating + Perl code in the expression at run time, and the code can refer to the + expression itself. A Perl pattern using code interpolation to solve the + parentheses problem can be created like this: $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; The (?p{...}) item interpolates Perl code at run time, and in this case - refers recursively to the pattern in which it appears. Obviously, PCRE - cannot support the interpolation of Perl code. Instead, it supports - some special syntax for recursion of the entire pattern, and also for - individual subpattern recursion. + refers recursively to the pattern in which it appears. + + Obviously, PCRE cannot support the interpolation of Perl code. Instead, + it supports special syntax for recursion of the entire pattern, and + also for individual subpattern recursion. After its introduction in + PCRE and Python, this kind of recursion was introduced into Perl at + release 5.10. - The special item that consists of (? followed by a number greater than + A special item that consists of (? followed by a number greater than zero and a closing parenthesis is a recursive call of the subpattern of - the given number, provided that it occurs inside that subpattern. (If - not, it is a "subroutine" call, which is described in the next sec- - tion.) The special item (?R) is a recursive call of the entire regular - expression. - - A recursive subpattern call is always treated as an atomic group. That - is, once it has matched some of the subject string, it is never re- - entered, even if it contains untried alternatives and there is a subse- - quent matching failure. + the given number, provided that it occurs inside that subpattern. (If + not, it is a "subroutine" call, which is described in the next sec- + tion.) The special item (?R) or (?0) is a recursive call of the entire + regular expression. + + In PCRE (like Python, but unlike Perl), a recursive subpattern call is + always treated as an atomic group. That is, once it has matched some of + the subject string, it is never re-entered, even if it contains untried + alternatives and there is a subsequent matching failure. - This PCRE pattern solves the nested parentheses problem (assume the + This PCRE pattern solves the nested parentheses problem (assume the PCRE_EXTENDED option is set so that white space is ignored): \( ( (?>[^()]+) | (?R) )* \) - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a - recursive match of the pattern itself (that is, a correctly parenthe- + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a + recursive match of the pattern itself (that is, a correctly parenthe- sized substring). Finally there is a closing parenthesis. - If this were part of a larger pattern, you would not want to recurse + If this were part of a larger pattern, you would not want to recurse the entire pattern, so instead you could use this: ( \( ( (?>[^()]+) | (?1) )* \) ) - We have put the pattern into parentheses, and caused the recursion to - refer to them instead of the whole pattern. In a larger pattern, keep- - ing track of parenthesis numbers can be tricky. It may be more conve- - nient to use named parentheses instead. For this, PCRE uses (?P>name), - which is an extension to the Python syntax that PCRE uses for named - parentheses (Perl does not provide named parentheses). We could rewrite - the above example as follows: - - (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) ) - - This particular example pattern contains nested unlimited repeats, and - so the use of atomic grouping for matching strings of non-parentheses - is important when applying the pattern to strings that do not match. - For example, when this pattern is applied to + We have put the pattern into parentheses, and caused the recursion to + refer to them instead of the whole pattern. + + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. (A Perl + 5.10 feature.) Instead of (?1) in the pattern above you can write + (?-2) to refer to the second most recently opened parentheses preceding + the recursion. In other words, a negative number counts capturing + parentheses leftwards from the point at which it is encountered. + + It is also possible to refer to subsequently opened parentheses, by + writing references such as (?+2). However, these cannot be recursive + because the reference is not inside the parentheses that are refer- + enced. They are always "subroutine" calls, as described in the next + section. + + An alternative approach is to use named parentheses instead. The Perl + syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also + supported. We could rewrite the above example as follows: + + (?<pn> \( ( (?>[^()]+) | (?&pn) )* \) ) + + If there is more than one subpattern with the same name, the earliest + one is used. + + This particular example pattern that we have been looking at contains + nested unlimited repeats, and so the use of atomic grouping for match- + ing strings of non-parentheses is important when applying the pattern + to strings that do not match. For example, when this pattern is applied + to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - it yields "no match" quickly. However, if atomic grouping is not used, - the match runs for a very long time indeed because there are so many - different ways the + and * repeats can carve up the subject, and all + it yields "no match" quickly. However, if atomic grouping is not used, + the match runs for a very long time indeed because there are so many + different ways the + and * repeats can carve up the subject, and all have to be tested before failure can be reported. At the end of a match, the values set for any capturing subpatterns are those from the outermost level of the recursion at which the subpattern - value is set. If you want to obtain intermediate values, a callout - function can be used (see the next section and the pcrecallout documen- - tation). If the pattern above is matched against + value is set. If you want to obtain intermediate values, a callout + function can be used (see below and the pcrecallout documentation). If + the pattern above is matched against (ab(cd)ef) - the value for the capturing parentheses is "ef", which is the last - value taken on at the top level. If additional parentheses are added, + the value for the capturing parentheses is "ef", which is the last + value taken on at the top level. If additional parentheses are added, giving \( ( ( (?>[^()]+) | (?R) )* ) \) ^ ^ ^ ^ - the string they capture is "ab(cd)ef", the contents of the top level - parentheses. If there are more than 15 capturing parentheses in a pat- + the string they capture is "ab(cd)ef", the contents of the top level + parentheses. If there are more than 15 capturing parentheses in a pat- tern, PCRE has to obtain extra memory to store data during a recursion, - which it does by using pcre_malloc, freeing it via pcre_free after- - wards. If no memory can be obtained, the match fails with the + which it does by using pcre_malloc, freeing it via pcre_free after- + wards. If no memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- ted at the outer level. < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - In this pattern, (?(R) is the start of a conditional subpattern, with - two different alternatives for the recursive and non-recursive cases. + In this pattern, (?(R) is the start of a conditional subpattern, with + two different alternatives for the recursive and non-recursive cases. The (?R) item is the actual recursive call. SUBPATTERNS AS SUBROUTINES If the syntax for a recursive subpattern reference (either by number or - by name) is used outside the parentheses to which it refers, it oper- - ates like a subroutine in a programming language. An earlier example - pointed out that the pattern + by name) is used outside the parentheses to which it refers, it oper- + ates like a subroutine in a programming language. The "called" subpat- + tern may be defined before or after the reference. A numbered reference + can be absolute or relative, as in these examples: + + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... + + An earlier example pointed out that the pattern (sens|respons)e and \1ibility @@ -3996,52 +4825,567 @@ (sens|respons)e and (?1)ibility is used, it does match "sense and responsibility" as well as the other - two strings. Such references, if given numerically, must follow the - subpattern to which they refer. However, named references can refer to - later subpatterns. + two strings. Another example is given in the discussion of DEFINE + above. Like recursive subpatterns, a "subroutine" call is always treated as an - atomic group. That is, once it has matched some of the subject string, - it is never re-entered, even if it contains untried alternatives and + atomic group. That is, once it has matched some of the subject string, + it is never re-entered, even if it contains untried alternatives and there is a subsequent matching failure. + When a subpattern is used as a subroutine, processing options such as + case-independence are fixed when the subpattern is defined. They cannot + be changed for different calls. For example, consider this pattern: + + (abc)(?i:(?-1)) + + It matches "abcabc". It does not match "abcABC" because the change of + processing option does not affect the called subpattern. + + +ONIGURUMA SUBROUTINE SYNTAX + + For compatibility with Oniguruma, the non-Perl syntax \g followed by a + name or a number enclosed either in angle brackets or single quotes, is + an alternative syntax for referencing a subpattern as a subroutine, + possibly recursively. Here are two of the examples used above, rewrit- + ten using this syntax: + + (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) + (sens|respons)e and \g'1'ibility + + PCRE supports an extension to Oniguruma: if a number is preceded by a + plus or a minus sign it is taken as a relative reference. For example: + + (abc)(?i:\g<-1>) + + Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not + synonymous. The former is a back reference; the latter is a subroutine + call. + CALLOUTS Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. + Perl code to be obeyed in the middle of matching a regular expression. This makes it possible, amongst other things, to extract different sub- strings that match the same pair of parentheses when there is a repeti- tion. PCRE provides a similar feature, but of course it cannot obey arbitrary Perl code. The feature is called "callout". The caller of PCRE provides - an external function by putting its entry point in the global variable - pcre_callout. By default, this variable contains NULL, which disables + an external function by putting its entry point in the global variable + pcre_callout. By default, this variable contains NULL, which disables all calling out. - Within a regular expression, (?C) indicates the points at which the - external function is to be called. If you want to identify different - callout points, you can put a number less than 256 after the letter C. - The default value is zero. For example, this pattern has two callout + Within a regular expression, (?C) indicates the points at which the + external function is to be called. If you want to identify different + callout points, you can put a number less than 256 after the letter C. + The default value is zero. For example, this pattern has two callout points: (?C1)abc(?C2)def If the PCRE_AUTO_CALLOUT flag is passed to pcre_compile(), callouts are - automatically installed before each item in the pattern. They are all + automatically installed before each item in the pattern. They are all numbered 255. During matching, when PCRE reaches a callout point (and pcre_callout is - set), the external function is called. It is provided with the number - of the callout, the position in the pattern, and, optionally, one item - of data originally supplied by the caller of pcre_exec(). The callout - function may cause matching to proceed, to backtrack, or to fail alto- + set), the external function is called. It is provided with the number + of the callout, the position in the pattern, and, optionally, one item + of data originally supplied by the caller of pcre_exec(). The callout + function may cause matching to proceed, to backtrack, or to fail alto- gether. A complete description of the interface to the callout function is given in the pcrecallout documentation. -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + +BACKTRACKING CONTROL + + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + which are described in the Perl documentation as "experimental and sub- + ject to change or removal in a future version of Perl". It goes on to + say: "Their usage in production code should be noted to avoid problems + during upgrades." The same remarks apply to the PCRE features described + in this section. + + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using + pcre_exec(), which uses a backtracking algorithm. With the exception of + (*FAIL), which behaves like a failing negative assertion, they cause an + error if encountered by pcre_dfa_exec(). + + The new verbs make use of what was previously invalid syntax: an open- + ing parenthesis followed by an asterisk. In Perl, they are generally of + the form (*VERB:ARG) but PCRE does not support the use of arguments, so + its general form is just (*VERB). Any number of these verbs may occur + in a pattern. There are two kinds: + + Verbs that act immediately + + The following verbs act as soon as they are encountered: + + (*ACCEPT) + + This verb causes the match to end successfully, skipping the remainder + of the pattern. When inside a recursion, only the innermost pattern is + ended immediately. PCRE differs from Perl in what happens if the + (*ACCEPT) is inside capturing parentheses. In Perl, the data so far is + captured: in PCRE no data is captured. For example: + + A(A|B(*ACCEPT)|C)D + + This matches "AB", "AAD", or "ACD", but when it matches "AB", no data + is captured. + + (*FAIL) or (*F) + + This verb causes the match to fail, forcing backtracking to occur. It + is equivalent to (?!) but easier to read. The Perl documentation notes + that it is probably useful only when combined with (?{}) or (??{}). + Those are, of course, Perl features that are not present in PCRE. The + nearest equivalent is the callout feature, as for example in this pat- + tern: + + a+(?C)(*FAIL) + + A match with the string "aaaa" always fails, but the callout is taken + before each backtrack happens (in this example, 10 times). + + Verbs that act after backtracking + + The following verbs do nothing when they are encountered. Matching con- + tinues with what follows, but if there is no subsequent match, a fail- + ure is forced. The verbs differ in exactly what kind of failure + occurs. + + (*COMMIT) + + This verb causes the whole match to fail outright if the rest of the + pattern does not match. Even if the pattern is unanchored, no further + attempts to find a match by advancing the start point take place. Once + (*COMMIT) has been passed, pcre_exec() is committed to finding a match + at the current starting point, or not at all. For example: + + a+(*COMMIT)b + + This matches "xxaab" but not "aacaab". It can be thought of as a kind + of dynamic anchor, or "I've started, so I must finish." + + (*PRUNE) + + This verb causes the match to fail at the current position if the rest + of the pattern does not match. If the pattern is unanchored, the normal + "bumpalong" advance to the next starting character then happens. Back- + tracking can occur as usual to the left of (*PRUNE), or when matching + to the right of (*PRUNE), but if there is no match to the right, back- + tracking cannot cross (*PRUNE). In simple cases, the use of (*PRUNE) + is just an alternative to an atomic group or possessive quantifier, but + there are some uses of (*PRUNE) that cannot be expressed in any other + way. + + (*SKIP) + + This verb is like (*PRUNE), except that if the pattern is unanchored, + the "bumpalong" advance is not to the next character, but to the posi- + tion in the subject where (*SKIP) was encountered. (*SKIP) signifies + that whatever text was matched leading up to it cannot be part of a + successful match. Consider: + + a+(*SKIP)b + + If the subject is "aaaac...", after the first match attempt fails + (starting at the first character in the string), the starting point + skips on to start the next attempt at "c". Note that a possessive quan- + tifer does not have the same effect in this example; although it would + suppress backtracking during the first match attempt, the second + attempt would start at the second character instead of skipping on to + "c". + + (*THEN) + + This verb causes a skip to the next alternation if the rest of the pat- + tern does not match. That is, it cancels pending backtracking, but only + within the current alternation. Its name comes from the observation + that it can be used for a pattern-based if-then-else block: + + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... + + If the COND1 pattern matches, FOO is tried (and possibly further items + after the end of the group if FOO succeeds); on failure the matcher + skips to the second alternative and tries COND2, without backtracking + into COND1. If (*THEN) is used outside of any alternation, it acts + exactly like (*PRUNE). + + +SEE ALSO + + pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 11 April 2009 + Copyright (c) 1997-2009 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRESYNTAX(3) PCRESYNTAX(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE REGULAR EXPRESSION SYNTAX SUMMARY + + The full syntax and semantics of the regular expressions that are sup- + ported by PCRE are described in the pcrepattern documentation. This + document contains just a quick-reference summary of the syntax. + + +QUOTING + + \x where x is non-alphanumeric is a literal x + \Q...\E treat enclosed characters as literal + + +CHARACTERS + + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any character + \e escape (hex 1B) + \f formfeed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \ddd character with octal code ddd, or backreference + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. + + +CHARACTER TYPES + + . any character except newline; + in dotall mode, any character whatsoever + \C one byte, even in UTF-8 mode (best avoided) + \d a decimal digit + \D a character that is not a decimal digit + \h a horizontal whitespace character + \H a character that is not a horizontal whitespace character + \p{xx} a character with the xx property + \P{xx} a character without the xx property + \R a newline sequence + \s a whitespace character + \S a character that is not a whitespace character + \v a vertical whitespace character + \V a character that is not a vertical whitespace character + \w a "word" character + \W a "non-word" character + \X an extended Unicode sequence + + In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters. + + +GENERAL CATEGORY PROPERTY CODES FOR \p and \P + + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator + + +SCRIPT NAMES FOR \p AND \P + + Arabic, Armenian, Balinese, Bengali, Bopomofo, Braille, Buginese, + Buhid, Canadian_Aboriginal, Carian, Cham, Cherokee, Common, Coptic, Cu- + neiform, Cypriot, Cyrillic, Deseret, Devanagari, Ethiopic, Georgian, + Glagolitic, Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, + Hebrew, Hiragana, Inherited, Kannada, Katakana, Kayah_Li, Kharoshthi, + Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lycian, Lydian, Malayalam, + Mongolian, Myanmar, New_Tai_Lue, Nko, Ogham, Old_Italic, Old_Persian, + Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Saurash- + tra, Shavian, Sinhala, Sudanese, Syloti_Nagri, Syriac, Tagalog, Tag- + banwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, + Ugaritic, Vai, Yi. + + +CHARACTER CLASSES + + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set + + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space whitespace + upper upper case letter + word same as \w + xdigit hexadecimal digit + + In PCRE, POSIX character set names recognize only ASCII characters. You + can use \Q...\E inside a character class. + + +QUANTIFIERS + + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy + + +ANCHORS AND SIMPLE ASSERTIONS + + \b word boundary (only ASCII letters recognized) + \B not a word boundary + ^ start of subject + also after internal newline in multiline mode + \A start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \Z end of subject + also before newline at end of subject + \z end of subject + \G first matching position in subject + + +MATCH POINT RESET + + \K reset start of match + + +ALTERNATION + + expr|expr|expr... + + +CAPTURING + + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative + + +ATOMIC GROUPS + + (?>...) atomic, non-capturing group + + +COMMENT + + (?#....) comment (not nestable) + + +OPTION SETTING + + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) + + The following is recognized only at the start of a pattern or after one + of the newline-setting options with similar syntax: + + (*UTF8) set UTF-8 mode + + +LOOKAHEAD AND LOOKBEHIND ASSERTIONS + + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind + + Each top-level branch of a look behind must be of a fixed length. + + +BACKREFERENCES + + \n reference by number (can be ambiguous) + \gn reference by number + \g{n} reference by number + \g{-n} relative reference by number + \k<name> reference by name (Perl) + \k'name' reference by name (Perl) + \g{name} reference by name (Perl) + \k{name} reference by name (.NET) + (?P=name) reference by name (Python) + + +SUBROUTINE REFERENCES (POSSIBLY RECURSIVE) + + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \g<name> call subpattern by name (Oniguruma) + \g'name' call subpattern by name (Oniguruma) + \g<n> call subpattern by absolute number (Oniguruma) + \g'n' call subpattern by absolute number (Oniguruma) + \g<+n> call subpattern by relative number (PCRE extension) + \g'+n' call subpattern by relative number (PCRE extension) + \g<-n> call subpattern by relative number (PCRE extension) + \g'-n' call subpattern by relative number (PCRE extension) + + +CONDITIONAL PATTERNS + + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition + + +BACKTRACKING CONTROL + + The following act immediately they are reached: + + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) + + The following act only when a subsequent match failure causes a back- + track to reach them. They all force a match failure, but they differ in + what happens afterwards. Those that advance the start-of-match point do + so only if the pattern is not anchored. + + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*SKIP) advance start to current matching position + (*THEN) local failure, backtrack to next alternation + + +NEWLINE CONVENTIONS + + These are recognized only at the very start of the pattern or after a + (*BSR_...) or (*UTF8) option. + + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence + + +WHAT \R MATCHES + + These are recognized only at the very start of the pattern or after a + (*...) option that sets the newline convention or UTF-8 mode. + + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence + + +CALLOUTS + + (?C) callout + (?Cn) callout with data n + + +SEE ALSO + + pcrepattern(3), pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 11 April 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -4121,12 +5465,13 @@ If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL - (-13). + (-13). You can use the PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to + find out if a compiled pattern can be used for partial matching. EXAMPLE OF PARTIAL MATCHING USING PCRETEST - If the escape sequence \P is present in a pcretest data line, the + If the escape sequence \P is present in a pcretest data line, the PCRE_PARTIAL flag is used for the match. Here is a run of pcretest that uses the date example quoted above: @@ -4143,13 +5488,13 @@ data> j\P No match - The first data string is matched completely, so pcretest shows the - matched substrings. The remaining four strings do not match the com- - plete pattern, but the first two are partial matches. The same test, - using DFA matching (by means of the \D escape sequence), produces the - following output: + The first data string is matched completely, so pcretest shows the + matched substrings. The remaining four strings do not match the com- + plete pattern, but the first two are partial matches. The same test, + using pcre_dfa_exec() matching (by means of the \D escape sequence), + produces the following output: - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 25jun04\P\D 0: 25jun04 data> 23dec3\P\D @@ -4161,21 +5506,22 @@ data> j\P\D No match - Notice that in this case the portion of the string that was matched is + Notice that in this case the portion of the string that was matched is made available. MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() When a partial match has been found using pcre_dfa_exec(), it is possi- - ble to continue the match by providing additional subject data and - calling pcre_dfa_exec() again with the PCRE_DFA_RESTART option and the - same working space (where details of the previous partial match are - stored). Here is an example using pcretest, where the \R escape - sequence sets the PCRE_DFA_RESTART option and the \D escape sequence - requests the use of pcre_dfa_exec(): + ble to continue the match by providing additional subject data and + calling pcre_dfa_exec() again with the same compiled regular expres- + sion, this time setting the PCRE_DFA_RESTART option. You must also pass + the same working space as before, because this is where details of the + previous partial match are stored. Here is an example using pcretest, + using the \R escape sequence to set the PCRE_DFA_RESTART option (\P and + \D are as above): - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 23ja\P\D Partial match: 23ja data> n05\R\D @@ -4188,29 +5534,29 @@ matched string. It is up to the calling program to do that if it needs to. - This facility can be used to pass very long subject strings to - pcre_dfa_exec(). However, some care is needed for certain types of pat- - tern. - - 1. If the pattern contains tests for the beginning or end of a line, - you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropri- - ate, when the subject string for any call does not contain the begin- + You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial + matching over multiple segments. This facility can be used to pass very + long subject strings to pcre_dfa_exec(). However, some care is needed + for certain types of pattern. + + 1. If the pattern contains tests for the beginning or end of a line, + you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropri- + ate, when the subject string for any call does not contain the begin- ning or end of a line. - 2. If the pattern contains backward assertions (including \b or \B), - you need to arrange for some overlap in the subject strings to allow - for this. For example, you could pass the subject in chunks that were - 500 bytes long, but in a buffer of 700 bytes, with the starting offset + 2. If the pattern contains backward assertions (including \b or \B), + you need to arrange for some overlap in the subject strings to allow + for this. For example, you could pass the subject in chunks that are + 500 bytes long, but in a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 bytes at the start of the buffer. - 3. Matching a subject string that is split into multiple segments does - not always produce exactly the same result as matching over one single - long string. The difference arises when there are multiple matching - possibilities, because a partial match result is given only when there - are no completed matches in a call to fBpcre_dfa_exec(). This means - that as soon as the shortest match has been found, continuation to a - new subject segment is no longer possible. Consider this pcretest - example: + 3. Matching a subject string that is split into multiple segments does + not always produce exactly the same result as matching over one single + long string. The difference arises when there are multiple matching + possibilities, because a partial match result is given only when there + are no completed matches in a call to pcre_dfa_exec(). This means that + as soon as the shortest match has been found, continuation to a new + subject segment is no longer possible. Consider this pcretest example: re> /dog(sbody)?/ data> do\P\D @@ -4236,21 +5582,31 @@ 1234|3789 - If the first part of the subject is "ABC123", a partial match of the - first alternative is found at offset 3. There is no partial match for + If the first part of the subject is "ABC123", a partial match of the + first alternative is found at offset 3. There is no partial match for the second alternative, because such a match does not start at the same - point in the subject string. Attempting to continue with the string + point in the subject string. Attempting to continue with the string "789" does not yield a match because only those alternatives that match - at one point in the subject are remembered. The problem arises because - the start of the second alternative matches within the first alterna- + at one point in the subject are remembered. The problem arises because + the start of the second alternative matches within the first alterna- tive. There is no problem with anchored patterns or patterns such as: 1234|ABCD where no string can be a partial match for both alternatives. -Last updated: 16 January 2006 -Copyright (c) 1997-2006 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 04 June 2007 + Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -4274,7 +5630,9 @@ ent host and run them there. This works even if the new host has the opposite endianness to the one on which the patterns were compiled. There may be a small performance penalty, but it should be insignifi- - cant. + cant. However, compiling regular expressions with one version of PCRE + for use with a different version is not guaranteed to work and may + cause crashes. SAVING A COMPILED PATTERN @@ -4357,19 +5715,22 @@ COMPATIBILITY WITH DIFFERENT PCRE RELEASES - The layout of the control block that is at the start of the data that - makes up a compiled pattern was changed for release 5.0. If you have - any saved patterns that were compiled with previous releases (not a - facility that was previously advertised), you will have to recompile - them for release 5.0. However, from now on, it should be possible to - make changes in a compatible manner. - - Notwithstanding the above, if you have any saved patterns in UTF-8 mode - that use \p or \P that were compiled with any release up to and includ- - ing 6.4, you will have to recompile them for release 6.5 and above. + In general, it is safest to recompile all saved patterns when you + update to a new PCRE release, though not all updates actually require + this. Recompiling is definitely needed for release 7.2. -Last updated: 01 February 2006 -Copyright (c) 1997-2006 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 13 June 2007 + Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -4382,14 +5743,70 @@ PCRE PERFORMANCE - Certain items that may appear in regular expression patterns are more - efficient than others. It is more efficient to use a character class - like [aeiou] than a set of alternatives such as (a|e|i|o|u). In gen- - eral, the simplest construction that provides the required behaviour is - usually the most efficient. Jeffrey Friedl's book contains a lot of - useful general discussion about optimizing regular expressions for - efficient performance. This document contains a few observations about - PCRE. + Two aspects of performance are discussed below: memory usage and pro- + cessing time. The way you express your pattern as a regular expression + can affect both of them. + + +MEMORY USAGE + + Patterns are compiled by PCRE into a reasonably efficient byte code, so + that most simple patterns do not use much memory. However, there is one + case where memory usage can be unexpectedly large. When a parenthesized + subpattern has a quantifier with a minimum greater than 1 and/or a lim- + ited maximum, the whole subpattern is repeated in the compiled code. + For example, the pattern + + (abc|def){2,4} + + is compiled as if it were + + (abc|def)(abc|def)((abc|def)(abc|def)?)? + + (Technical aside: It is done this way so that backtrack points within + each of the repetitions can be independently maintained.) + + For regular expressions whose quantifiers use only small numbers, this + is not usually a problem. However, if the numbers are large, and par- + ticularly if such repetitions are nested, the memory usage can become + an embarrassment. For example, the very simple pattern + + ((ab){1,1000}c){1,3} + + uses 51K bytes when compiled. When PCRE is compiled with its default + internal pointer size of two bytes, the size limit on a compiled pat- + tern is 64K, and this is reached with the above pattern if the outer + repetition is increased from 3 to 4. PCRE can be compiled to use larger + internal pointers and thus handle larger compiled patterns, but it is + better to try to rewrite your pattern to use less memory if you can. + + One way of reducing the memory usage for such patterns is to make use + of PCRE's "subroutine" facility. Re-writing the above pattern as + + ((ab)(?2){0,999}c)(?1){0,2} + + reduces the memory requirements to 18K, and indeed it remains under 20K + even with the outer repetition increased to 100. However, this pattern + is not exactly equivalent, because the "subroutine" calls are treated + as atomic groups into which there can be no backtracking if there is a + subsequent matching failure. Therefore, PCRE cannot do this kind of + rewriting automatically. Furthermore, there is a noticeable loss of + speed when executing the modified pattern. Nevertheless, if the atomic + grouping is not a problem and the loss of speed is acceptable, this + kind of rewriting will allow you to process patterns that PCRE cannot + otherwise handle. + + +PROCESSING TIME + + Certain items in regular expression patterns are processed more effi- + ciently than others. It is more efficient to use a character class like + [aeiou] than a set of single-character alternatives such as + (a|e|i|o|u). In general, the simplest construction that provides the + required behaviour is usually the most efficient. Jeffrey Friedl's book + contains a lot of useful general discussion about optimizing regular + expressions for efficient performance. This document contains a few + observations about PCRE. Using Unicode character properties (the \p, \P, and \X escapes) is slow, because PCRE has to scan a structure that contains data for over @@ -4423,15 +5840,15 @@ take a long time to run when applied to a string that does not match. Consider the pattern fragment - (a+)* + ^(a+)* - This can match "aaaa" in 33 different ways, and this number increases + This can match "aaaa" in 16 different ways, and this number increases very rapidly as the string gets longer. (The * repeat can match 0, 1, - 2, 3, or 4 times, and for each of those cases other than 0, the + + 2, 3, or 4 times, and for each of those cases other than 0 or 4, the + repeats can match different numbers of times.) When the remainder of the pattern is such that the entire match is going to fail, PCRE has in principle to try every possible variation, and this can take an - extremely long time. + extremely long time, even for relatively short strings. An optimization catches some of the more simple cases such as @@ -4452,8 +5869,18 @@ In many cases, the solution to this kind of performance issue is to use an atomic group or a possessive quantifier. -Last updated: 28 February 2005 -Copyright (c) 1997-2005 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 06 March 2007 + Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -4493,12 +5920,12 @@ command for linking an application that uses them. Because the POSIX functions call the native ones, it is also necessary to add -lpcre. - I have implemented only those option bits that can be reasonably mapped - to PCRE native options. In addition, the option REG_EXTENDED is defined - with the value zero. This has no effect, but since programs that are - written to the POSIX interface often use it, this makes it easier to - slot in PCRE as a replacement library. Other POSIX options are not even - defined. + I have implemented only those POSIX option bits that can be reasonably + mapped to PCRE native options. In addition, the option REG_EXTENDED is + defined with the value zero. This has no effect, but since programs + that are written to the POSIX interface often use it, this makes it + easier to slot in PCRE as a replacement library. Other POSIX options + are not even defined. When PCRE is called via these functions, it is only the API that is POSIX-like in style. The syntax and semantics of the regular expres- @@ -4578,9 +6005,9 @@ MATCHING NEWLINE CHARACTERS This area is not simple, because POSIX and Perl take different views of - things. It is not possible to get PCRE to obey POSIX semantics, but - then PCRE was never intended to be a POSIX engine. The following table - lists the different possibilities for matching newline characters in + things. It is not possible to get PCRE to obey POSIX semantics, but + then PCRE was never intended to be a POSIX engine. The following table + lists the different possibilities for matching newline characters in PCRE: Default Change with @@ -4602,30 +6029,49 @@ ^ matches \n in middle no REG_NEWLINE PCRE's behaviour is the same as Perl's, except that there is no equiva- - lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is + lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop newline from matching [^a]. - The default POSIX newline handling can be obtained by setting - PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE + The default POSIX newline handling can be obtained by setting + PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the REG_NEWLINE action. MATCHING A PATTERN - The function regexec() is called to match a compiled pattern preg - against a given string, which is terminated by a zero byte, subject to - the options in eflags. These can be: + The function regexec() is called to match a compiled pattern preg + against a given string, which is by default terminated by a zero byte + (but see REG_STARTEND below), subject to the options in eflags. These + can be: REG_NOTBOL The PCRE_NOTBOL option is set when calling the underlying PCRE matching function. + REG_NOTEMPTY + + The PCRE_NOTEMPTY option is set when calling the underlying PCRE match- + ing function. Note that REG_NOTEMPTY is not part of the POSIX standard. + However, setting this option can give more POSIX-like behaviour in some + situations. + REG_NOTEOL The PCRE_NOTEOL option is set when calling the underlying PCRE matching function. + REG_STARTEND + + The string is considered to start at string + pmatch[0].rm_so and to + have a terminating NUL located at string + pmatch[0].rm_eo (there need + not actually be a NUL at that location), regardless of the value of + nmatch. This is a BSD extension, compatible with but not specified by + IEEE Standard 1003.2 (POSIX.2), and should be used with caution in + software intended to be portable to other systems. Note that a non-zero + rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location + of the string, not how it is matched. + If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The nmatch and pmatch arguments of regexec() are ignored. @@ -4666,11 +6112,14 @@ AUTHOR Philip Hazel - University Computing Service, - Cambridge CB2 3QG, England. + University Computing Service + Cambridge CB2 3QH, England. -Last updated: 16 January 2006 -Copyright (c) 1997-2006 University of Cambridge. + +REVISION + + Last updated: 11 March 2009 + Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------ @@ -4758,14 +6207,42 @@ c. The "i"th argument has a suitable type for holding the string captured as the "i"th sub-pattern. If you pass in - NULL for the "i"th argument, or pass fewer arguments than + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the number of sub-patterns, "i"th captured sub-pattern is ignored. + CAVEAT: An optional sub-pattern that does not exist in the matched + string is assigned the empty string. Therefore, the following will + return false (because the empty string is not a valid number): + + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); + The matching interface supports at most 16 arguments per call. If you need more, consider using the more general interface pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch. + NOTE: Do not use no_arg, which is used internally to mark the end of a + list of optional arguments, as a placeholder for missing arguments, as + this can lead to segfaults. + + +QUOTING METACHARACTERS + + You can use the "QuoteMeta" operation to insert backslashes before all + potentially meaningful characters in a string. The returned string, + used as a regular expression, will exactly match the original string. + + Example: + string quoted = RE::QuoteMeta(unquoted); + + Note that it's legal to escape a character even if it has no special + meaning in a regular expression -- so this function does that. (This + also makes it identical to the perl function of the same name; see + "perldoc -f quotemeta".) For example, "1.5-2.0?" becomes + "1\.5\-2\.0\?". + PARTIAL MATCHES @@ -4978,7 +6455,12 @@ AUTHOR The C++ wrapper was contributed by Google Inc. - Copyright (c) 2005 Google Inc. + Copyright (c) 2007 Google Inc. + + +REVISION + + Last updated: 17 March 2009 ------------------------------------------------------------------------------ @@ -5045,8 +6527,18 @@ (for example) to the compile command to get round this problem. -Last updated: 09 September 2004 -Copyright (c) 1997-2004 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 23 January 2008 + Copyright (c) 1997-2008 University of Cambridge. ------------------------------------------------------------------------------ PCRESTACK(3) PCRESTACK(3) @@ -5099,7 +6591,7 @@ ter. For a long string, a lot of stack is required. Consider now this rewritten pattern, which matches exactly the same strings: - ([^<]++|<(?!inet)) + ([^<]++|<(?!inet))+ This uses very much less stack, because runs of characters that do not contain "<" are "swallowed" in one item inside the parentheses. Recur- @@ -5108,30 +6600,25 @@ quantifier is used to stop any backtracking into the runs of non-"<" characters, but that is not related to stack usage. + This example shows that one way of avoiding stack problems when match- + ing long subject strings is to write repeated parenthesized subpatterns + to match more than one character whenever possible. + + Compiling PCRE to use heap instead of stack + In environments where stack memory is constrained, you might want to compile PCRE to use heap memory instead of stack for remembering back- up points. This makes it run a lot more slowly, however. Details of how - to do this are given in the pcrebuild documentation. + to do this are given in the pcrebuild documentation. When built in this + way, instead of using the stack, PCRE obtains and frees memory by call- + ing the functions that are pointed to by the pcre_stack_malloc and + pcre_stack_free variables. By default, these point to malloc() and + free(), but you can replace the pointers to cause PCRE to use your own + functions. Since the block sizes are always the same, and are always + freed in reverse order, it may be possible to implement customized mem- + ory handlers that are more efficient than the standard functions. - In Unix-like environments, there is not often a problem with the stack, - though the default limit on stack size varies from system to system. - Values from 8Mb to 64Mb are common. You can find your default limit by - running the command: - - ulimit -s - - The effect of running out of stack is often SIGSEGV, though sometimes - an error message is given. You can normally increase the limit on stack - size by code such as this: - - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = 100*1024*1024; - setrlimit(RLIMIT_STACK, &rlim); - - This reads the current limits (soft and hard) using getrlimit(), then - attempts to increase the soft limit to 100Mb using setrlimit(). You - must do this before calling pcre_exec(). + Limiting PCRE's stack usage PCRE has an internal counter that can be used to limit the depth of recursion, and thus cause pcre_exec() to give an error code before it @@ -5144,10 +6631,50 @@ recursion. Thus, if you want to limit your stack usage to 8Mb, you should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can support around 128000 recursions. The pcretest test program - has a command line option (-S) that can be used to increase its stack. + has a command line option (-S) that can be used to increase the size of + its stack. + + Changing stack size in Unix-like systems + + In Unix-like environments, there is not often a problem with the stack + unless very long strings are involved, though the default limit on + stack size varies from system to system. Values from 8Mb to 64Mb are + common. You can find your default limit by running the command: + + ulimit -s + + Unfortunately, the effect of running out of stack is often SIGSEGV, + though sometimes a more explicit error message is given. You can nor- + mally increase the limit on stack size by code such as this: + + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); + + This reads the current limits (soft and hard) using getrlimit(), then + attempts to increase the soft limit to 100Mb using setrlimit(). You + must do this before calling pcre_exec(). + + Changing stack size in Mac OS X + + Using setrlimit(), as described above, should also work on Mac OS X. It + is also possible to set a stack size when linking a program. There is a + discussion about stack sizes in Mac OS X at this web site: + http://developer.apple.com/qa/qa2005/qa1419.html. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION -Last updated: 29 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + Last updated: 09 July 2008 + Copyright (c) 1997-2008 University of Cambridge. ------------------------------------------------------------------------------ Modified: freeswitch/trunk/libs/pcre/doc/pcre_compile.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_compile.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_compile.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, .ti +5n .B const char **\fIerrptr\fP, int *\fIerroffset\fP, @@ -17,8 +16,9 @@ .SH DESCRIPTION .rs .sp -This function compiles a regular expression into an internal form. Its -arguments are: +This function compiles a regular expression into an internal form. It is the +same as \fBpcre_compile2()\fP, except for the absence of the \fIerrorcodeptr\fP +argument. Its arguments are: .sp \fIpattern\fR A zero-terminated string containing the regular expression to be compiled @@ -30,33 +30,41 @@ .sp The option bits are: .sp - PCRE_ANCHORED Force pattern anchoring - PCRE_AUTO_CALLOUT Compile automatic callouts - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_DUPNAMES Allow duplicate names for subpatterns - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_FIRSTLINE Force matching to be before newline - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore whitespace and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF8 Run in UTF-8 mode + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) .sp PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and PCRE_NO_UTF8_CHECK. .P The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_compile2.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_compile2.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_compile2.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, .ti +5n .B int *\fIerrorcodeptr\fP, @@ -46,6 +45,8 @@ (not much use currently) PCRE_FIRSTLINE Force matching to be before newline PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence @@ -61,7 +62,9 @@ PCRE_NO_UTF8_CHECK. .P The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_config.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_config.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_config.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); . .SH DESCRIPTION @@ -26,7 +25,15 @@ PCRE_CONFIG_MATCH_LIMIT Internal resource limit PCRE_CONFIG_MATCH_LIMIT_RECURSION Internal recursion depth limit - PCRE_CONFIG_NEWLINE Value of the newline sequence + PCRE_CONFIG_NEWLINE Value of the default newline sequence: + 13 (0x000d) for CR + 10 (0x000a) for LF + 3338 (0x0d0a) for CRLF + -2 for ANYCRLF + -1 for ANY + PCRE_CONFIG_BSR Indicates what \eR matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only PCRE_CONFIG_POSIX_MALLOC_THRESHOLD Threshold of return slots, above which \fBmalloc()\fR is used by Modified: freeswitch/trunk/libs/pcre/doc/pcre_copy_named_substring.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_copy_named_substring.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_copy_named_substring.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_copy_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, Modified: freeswitch/trunk/libs/pcre/doc/pcre_copy_substring.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_copy_substring.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_copy_substring.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, .ti +5n .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, @@ -27,7 +26,7 @@ \fIbuffer\fP Buffer to receive the string \fIbuffersize\fP Size of buffer .sp -The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was +The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. .P There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/pcre_dfa_exec.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_dfa_exec.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_dfa_exec.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, @@ -20,9 +19,9 @@ .rs .sp This function matches a compiled regular expression against a given subject -string, using a DFA matching algorithm (\fInot\fP Perl-compatible). Note that -the main, Perl-compatible, matching function is \fBpcre_exec()\fP. The -arguments for this function are: +string, using an alternative matching algorithm that scans the subject string +just once (\fInot\fP Perl-compatible). Note that the main, Perl-compatible, +matching function is \fBpcre_exec()\fP. The arguments for this function are: .sp \fIcode\fP Points to the compiled pattern \fIextra\fP Points to an associated \fBpcre_extra\fP structure, @@ -40,12 +39,17 @@ The options are: .sp PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence PCRE_NOTBOL Subject is not the beginning of a line PCRE_NOTEOL Subject is not the end of a line PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) @@ -53,8 +57,8 @@ PCRE_DFA_SHORTEST Return only the shortest match PCRE_DFA_RESTART This is a restart after a partial match .sp -There are restrictions on what may appear in a pattern when matching using the -DFA algorithm is requested. Details are given in the +There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the .\" HREF \fBpcrematching\fP .\" @@ -71,7 +75,7 @@ .sp The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. For DFA matching, the \fImatch_limit\fP and +PCRE_EXTRA_TABLES. For this matching function, the \fImatch_limit\fP and \fImatch_limit_recursion\fP fields are not used, and must not be set. .P There is a complete description of the PCRE native API in the Modified: freeswitch/trunk/libs/pcre/doc/pcre_exec.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_exec.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_exec.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, @@ -35,19 +34,28 @@ The options are: .sp PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence PCRE_NEWLINE_CRLF Set CRLF as the newline sequence PCRE_NEWLINE_LF Set LF as the newline sequence PCRE_NOTBOL Subject is not the beginning of a line PCRE_NOTEOL Subject is not the end of a line PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match .sp There are restrictions on what may appear in a pattern when partial matching is -requested. +requested. For details, see the +.\" HREF +\fBpcrepartial\fP +.\" +page. .P A \fBpcre_extra\fP structure contains the following fields: .sp Modified: freeswitch/trunk/libs/pcre/doc/pcre_free_substring.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_free_substring.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_free_substring.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B void pcre_free_substring(const char *\fIstringptr\fP); . .SH DESCRIPTION Modified: freeswitch/trunk/libs/pcre/doc/pcre_free_substring_list.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_free_substring_list.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_free_substring_list.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B void pcre_free_substring_list(const char **\fIstringptr\fP); . .SH DESCRIPTION Modified: freeswitch/trunk/libs/pcre/doc/pcre_fullinfo.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_fullinfo.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_fullinfo.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B int \fIwhat\fP, void *\fIwhere\fP); @@ -31,13 +30,14 @@ -1 for start of string or after newline, or -2 otherwise - PCRE_INFO_FIRSTTABLE Table of first bytes - (after studying) + PCRE_INFO_FIRSTTABLE Table of first bytes (after studying) + PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used PCRE_INFO_LASTLITERAL Literal last byte required PCRE_INFO_NAMECOUNT Number of named subpatterns PCRE_INFO_NAMEENTRYSIZE Size of name table entry PCRE_INFO_NAMETABLE Pointer to name table - PCRE_INFO_OPTIONS Options used for compilation + PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried + PCRE_INFO_OPTIONS Option bits used for compilation PCRE_INFO_SIZE Size of compiled pattern PCRE_INFO_STUDYSIZE Size of study data .sp Modified: freeswitch/trunk/libs/pcre/doc/pcre_get_named_substring.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_get_named_substring.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_get_named_substring.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_get_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, @@ -30,9 +29,10 @@ \fIstringptr\fP Where to put the string pointer .sp The memory in which the substring is placed is obtained by calling -\fBpcre_malloc()\fP. The yield of the function is the length of the extracted -substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE_ERROR_NOSUBSTRING if the string name is invalid. +\fBpcre_malloc()\fP. The convenience function \fBpcre_free_substring()\fP can +be used to free it when it is no longer needed. The yield of the function is +the length of the extracted substring, PCRE_ERROR_NOMEMORY if sufficient memory +could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_get_stringnumber.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_get_stringnumber.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_get_stringnumber.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_get_stringnumber(const pcre *\fIcode\fP, .ti +5n .B const char *\fIname\fP); @@ -22,7 +21,10 @@ \fIname\fP Name whose number is required .sp The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. +found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed +(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by +\fBpcre_get_stringnumber()\fP. You can obtain the complete list by calling +\fBpcre_get_stringtable_entries()\fP. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_get_stringtable_entries.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_get_stringtable_entries.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_get_stringtable_entries.3 Mon Jun 8 18:51:30 2009 @@ -1,4 +1,4 @@ -.TH PCRE_GET_STRINGNUMBER 3 +.TH PCRE_GET_STRINGTABLE_ENTRIES 3 .SH NAME PCRE - Perl-compatible regular expressions .SH SYNOPSIS @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, .ti +5n .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); @@ -34,7 +33,7 @@ .\" HREF \fBpcreapi\fP .\" -page and a description of the POSIX API in the +page, and a description of the POSIX API in the .\" HREF \fBpcreposix\fP .\" Modified: freeswitch/trunk/libs/pcre/doc/pcre_get_substring.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_get_substring.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_get_substring.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, .ti +5n .B int \fIstringcount\fP, int \fIstringnumber\fP, @@ -27,9 +26,10 @@ \fIstringptr\fP Where to put the string pointer .sp The memory in which the substring is placed is obtained by calling -\fBpcre_malloc()\fP. The yield of the function is the length of the substring, -PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE_ERROR_NOSUBSTRING if the string number is invalid. +\fBpcre_malloc()\fP. The convenience function \fBpcre_free_substring()\fP can +be used to free it when it is no longer needed. The yield of the function is +the length of the substring, PCRE_ERROR_NOMEMORY if sufficient memory could not +be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_get_substring_list.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_get_substring_list.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_get_substring_list.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_get_substring_list(const char *\fIsubject\fP, .ti +5n .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" @@ -24,10 +23,12 @@ \fIlistptr\fP Where to put a pointer to the list .sp The memory in which the substrings and the list are placed is obtained by -calling \fBpcre_malloc()\fP. A pointer to a list of pointers is put in -the variable whose address is in \fIlistptr\fP. The list is terminated by a -NULL pointer. The yield of the function is zero on success or -PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained. +calling \fBpcre_malloc()\fP. The convenience function +\fBpcre_free_substring_list()\fP can be used to free it when it is no longer +needed. A pointer to a list of pointers is put in the variable whose address is +in \fIlistptr\fP. The list is terminated by a NULL pointer. The yield of the +function is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could +not be obtained. .P There is a complete description of the PCRE native API in the .\" HREF Modified: freeswitch/trunk/libs/pcre/doc/pcre_info.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_info.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_info.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int .B *\fIfirstcharptr\fP); . Modified: freeswitch/trunk/libs/pcre/doc/pcre_maketables.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_maketables.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_maketables.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B const unsigned char *pcre_maketables(void); . .SH DESCRIPTION Modified: freeswitch/trunk/libs/pcre/doc/pcre_refcount.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_refcount.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_refcount.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); . .SH DESCRIPTION Modified: freeswitch/trunk/libs/pcre/doc/pcre_study.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_study.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_study.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, .ti +5n .B const char **\fIerrptr\fP); Modified: freeswitch/trunk/libs/pcre/doc/pcre_version.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcre_version.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcre_version.3 Mon Jun 8 18:51:30 2009 @@ -7,7 +7,6 @@ .B #include <pcre.h> .PP .SM -.br .B char *pcre_version(void); . .SH DESCRIPTION Modified: freeswitch/trunk/libs/pcre/doc/pcreapi.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcreapi.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcreapi.3 Mon Jun 8 18:51:30 2009 @@ -7,14 +7,12 @@ .B #include <pcre.h> .PP .SM -.br .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, .ti +5n .B const char **\fIerrptr\fP, int *\fIerroffset\fP, .ti +5n .B const unsigned char *\fItableptr\fP); .PP -.br .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, .ti +5n .B int *\fIerrorcodeptr\fP, @@ -23,19 +21,16 @@ .ti +5n .B const unsigned char *\fItableptr\fP); .PP -.br .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, .ti +5n .B const char **\fIerrptr\fP); .PP -.br .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, .ti +5n .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); .PP -.br .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, @@ -44,7 +39,6 @@ .ti +5n .B int *\fIworkspace\fP, int \fIwscount\fP); .PP -.br .B int pcre_copy_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, @@ -53,14 +47,12 @@ .ti +5n .B char *\fIbuffer\fP, int \fIbuffersize\fP); .PP -.br .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, .ti +5n .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, .ti +5n .B int \fIbuffersize\fP); .PP -.br .B int pcre_get_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, @@ -69,76 +61,59 @@ .ti +5n .B const char **\fIstringptr\fP); .PP -.br .B int pcre_get_stringnumber(const pcre *\fIcode\fP, .ti +5n .B const char *\fIname\fP); .PP -.br .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, .ti +5n .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); .PP -.br .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, .ti +5n .B int \fIstringcount\fP, int \fIstringnumber\fP, .ti +5n .B const char **\fIstringptr\fP); .PP -.br .B int pcre_get_substring_list(const char *\fIsubject\fP, .ti +5n .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" .PP -.br .B void pcre_free_substring(const char *\fIstringptr\fP); .PP -.br .B void pcre_free_substring_list(const char **\fIstringptr\fP); .PP -.br .B const unsigned char *pcre_maketables(void); .PP -.br .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," .ti +5n .B int \fIwhat\fP, void *\fIwhere\fP); .PP -.br .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int .B *\fIfirstcharptr\fP); .PP -.br .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); .PP -.br .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); .PP -.br .B char *pcre_version(void); .PP -.br .B void *(*pcre_malloc)(size_t); .PP -.br .B void (*pcre_free)(void *); .PP -.br .B void *(*pcre_stack_malloc)(size_t); .PP -.br .B void (*pcre_stack_free)(void *); .PP -.br .B int (*pcre_callout)(pcre_callout_block *); . . .SH "PCRE API OVERVIEW" .rs .sp -PCRE has its own native API, which is described in this document. There is -also a set of wrapper functions that correspond to the POSIX regular expression +PCRE has its own native API, which is described in this document. There are +also some wrapper functions that correspond to the POSIX regular expression API. These are described in the .\" HREF \fBpcreposix\fP @@ -165,14 +140,14 @@ .\" HREF \fBpcresample\fP .\" -documentation describes how to run it. +documentation describes how to compile and run it. .P A second matching function, \fBpcre_dfa_exec()\fP, which is not Perl-compatible, is also provided. This uses a different algorithm for the matching. The alternative algorithm finds all possible matches (at a given -point in the subject). However, this algorithm does not return captured -substrings. A description of the two matching algorithms and their advantages -and disadvantages is given in the +point in the subject), and scans the subject just once. However, this algorithm +does not return captured substrings. A description of the two matching +algorithms and their advantages and disadvantages is given in the .\" HREF \fBpcrematching\fP .\" @@ -243,16 +218,47 @@ documentation. . . +.\" HTML <a name="newlines"></a> .SH NEWLINES -PCRE supports three different conventions for indicating line breaks in -strings: a single CR character, a single LF character, or the two-character -sequence CRLF. All three are used as "standard" by different operating systems. -When PCRE is built, a default can be specified. The default default is LF, -which is the Unix standard. When PCRE is run, the default can be overridden, -either when a pattern is compiled, or when it is matched. +.rs .sp +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +.P +Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE is built, a default can be specified. +The default default is LF, which is the Unix standard. When PCRE is run, the +default can be overridden, either when a pattern is compiled, or when it is +matched. +.P +At compile time, the newline convention can be specified by the \fIoptions\fP +argument of \fBpcre_compile()\fP, or it can be specified by special text at the +start of the pattern itself; this overrides any other settings. See the +.\" HREF +\fBpcrepattern\fP +.\" +page for details of the special character sequences. +.P In the PCRE documentation the word "newline" is used to mean "the character or -pair of characters that indicate a line break". +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +.\" HTML <a href="#execoptions"> +.\" </a> +section on \fBpcre_exec()\fP options +.\" +below. +.P +The choice of newline convention does not affect the interpretation of +the \en or \er escape sequences, nor does it affect what \eR matches, which is +controlled in a similar way, but by separate options. . . .SH MULTITHREADING @@ -276,7 +282,9 @@ .\" HREF \fBpcreprecompile\fP .\" -documentation. +documentation. However, compiling a regular expression with one version of PCRE +for use with a different version is not guaranteed to work and may cause +crashes. . . .SH "CHECKING BUILD-TIME OPTIONS" @@ -308,9 +316,18 @@ PCRE_CONFIG_NEWLINE .sp The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The three values that are supported -are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be -the standard sequence for your operating system. +that is recognized as meaning "newline". The four values that are supported +are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. +Though they are derived from ASCII, the same values are returned in EBCDIC +environments. The default should normally correspond to the standard sequence +for your operating system. +.sp + PCRE_CONFIG_BSR +.sp +The output is an integer whose value indicates what character sequences the \eR +escape sequence matches by default. A value of 0 means that \eR matches any +Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. .sp PCRE_CONFIG_LINK_SIZE .sp @@ -332,13 +349,13 @@ .sp PCRE_CONFIG_MATCH_LIMIT .sp -The output is an integer that gives the default limit for the number of +The output is a long integer that gives the default limit for the number of internal matching function calls in a \fBpcre_exec()\fP execution. Further details are given with \fBpcre_exec()\fP below. .sp PCRE_CONFIG_MATCH_LIMIT_RECURSION .sp -The output is an integer that gives the default limit for the depth of +The output is a long integer that gives the default limit for the depth of recursion when calling the internal matching function in a \fBpcre_exec()\fP execution. Further details are given with \fBpcre_exec()\fP below. .sp @@ -387,18 +404,19 @@ fully relocatable, because it may contain a copy of the \fItableptr\fP argument, which is an address (see below). .P -The \fIoptions\fP argument contains independent bits that affect the +The \fIoptions\fP argument contains various bit settings that affect the compilation. It should be zero if no options are required. The available -options are described below. Some of them, in particular, those that are -compatible with Perl, can also be set and unset from within the pattern (see -the detailed description in the +options are described below. Some of them (in particular, those that are +compatible with Perl, but also some others) can also be set and unset from +within the pattern (see the detailed description in the .\" HREF \fBpcrepattern\fP .\" -documentation). For these options, the contents of the \fIoptions\fP argument -specifies their initial settings at the start of compilation and execution. The -PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of -matching as well as at compile time. +documentation). For those options that can be different in different parts of +the pattern, the contents of the \fIoptions\fP argument specifies their initial +settings at the start of compilation and execution. The PCRE_ANCHORED and +PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at +compile time. .P If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately. Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns @@ -453,6 +471,15 @@ .\" documentation. .sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +.sp PCRE_CASELESS .sp If this bit is set, letters in the pattern match both upper and lower case @@ -480,8 +507,8 @@ including those that indicate newline. Without it, a dot does not match when the current position is at a newline. This option is equivalent to Perl's /s option, and it can be changed within a pattern by a (?s) option setting. A -negative class such as [^a] always matches newlines, independent of the setting -of this option. +negative class such as [^a] always matches newline characters, independent of +the setting of this option. .sp PCRE_DUPNAMES .sp @@ -525,6 +552,20 @@ the first newline in the subject string, though the matched text may continue over the newline. .sp + PCRE_JAVASCRIPT_COMPAT +.sp +If this option is set, PCRE's behaviour is changed in some ways so that it is +compatible with JavaScript rather than Perl. The changes are as follows: +.P +(1) A lone closing square bracket in a pattern causes a compile-time error, +because this is illegal in JavaScript (by default it is treated as a data +character). Thus, the pattern AB]CD becomes illegal when this option is set. +.P +(2) At run time, a back reference to an unset subpattern group matches an empty +string (by default this causes the current matching alternative to fail). A +pattern such as (\e1)(a) succeeds when this option is set (assuming it can find +an "a" in the subject), whereas it fails by default, for Perl compatibility. +.sp PCRE_MULTILINE .sp By default, PCRE treats the subject string as consisting of a single line of @@ -544,18 +585,37 @@ PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY .sp These options override the default newline definition that was chosen when PCRE was built. Setting the first or the second specifies that a newline is -indicated by a single character (CR or LF, respectively). Setting both of them -specifies that a newline is indicated by the two-character CRLF sequence. For -convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time -that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is -set, and an unescaped # outside a character class is encountered. This -indicates a comment that lasts until after the next newline. +indicated by a single character (CR or LF, respectively). Setting +PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character +CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three +preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies +that any Unicode newline sequence should be recognized. The Unicode newline +sequences are the three just mentioned, plus the single characters VT (vertical +tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line +separator, U+2028), and PS (paragraph separator, U+2029). The last two are +recognized only in UTF-8 mode. +.P +The newline setting in the options word uses three bits that are treated +as a number, giving eight possibilities. Currently only six are used (default +plus the five values above). This means that if you set more than one newline +option, the combination may or may not be sensible. For example, +PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but +other combinations may yield unused numbers and cause an error. +.P +The only time that a line break is specially recognized when compiling a +pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character +class is encountered. This indicates a comment that lasts until after the next +line break sequence. In other circumstances, line break sequences are treated +as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated +as whitespace characters and are therefore ignored. .P -The newline option set at compile time becomes the default that is used for -\fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. +The newline option that is set at compile time becomes the default that is used +for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. .sp PCRE_NO_AUTO_CAPTURE .sp @@ -591,14 +651,22 @@ PCRE_NO_UTF8_CHECK .sp When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. If an invalid UTF-8 sequence of bytes is found, -\fBpcre_compile()\fP returns an error. If you already know that your pattern is -valid, and you want to skip this check for performance reasons, you can set the -PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid -UTF-8 string as a pattern is undefined. It may cause your program to crash. -Note that this option can also be passed to \fBpcre_exec()\fP and -\fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject -strings. +automatically checked. There is a discussion about the +.\" HTML <a href="pcre.html#utf8strings"> +.\" </a> +validity of UTF-8 strings +.\" +in the main +.\" HREF +\fBpcre\fP +.\" +page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP +returns an error. If you already know that your pattern is valid, and you want +to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK +option. When it is set, the effect of passing an invalid UTF-8 string as a +pattern is undefined. It may cause your program to crash. Note that this option +can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress +the UTF-8 validity checking of subject strings. . . .SH "COMPILATION ERROR CODES" @@ -606,7 +674,8 @@ .sp The following table lists the error codes than may be returned by \fBpcre_compile2()\fP, along with the error messages that may be returned by -both compiling functions. +both compiling functions. As PCRE has developed, some error codes have fallen +out of use. To avoid confusion, they have not been re-used. .sp 0 no error 1 \e at end of pattern @@ -618,17 +687,17 @@ 7 invalid escape sequence in character class 8 range out of order in character class 9 nothing to repeat - 10 operand of unlimited repeat could match the empty string + 10 [this code is not in use] 11 internal error: unexpected repeat - 12 unrecognized character after (? + 12 unrecognized character after (? or (?- 13 POSIX named classes are supported only within a class 14 missing ) 15 reference to non-existent subpattern 16 erroffset passed as NULL 17 unknown option bit(s) set 18 missing ) after comment - 19 parentheses nested too deeply - 20 regular expression too large + 19 [this code is not in use] + 20 regular expression is too large 21 failed to get memory 22 unmatched parentheses 23 internal error: code overflow @@ -637,11 +706,11 @@ 26 malformed number or name after (?( 27 conditional group contains more than two branches 28 assertion expected after (?( - 29 (?R or (?digits must be followed by ) + 29 (?R or (?[+-]digits must be followed by ) 30 unknown POSIX class name 31 POSIX collating elements are not supported 32 this version of PCRE is not compiled with PCRE_UTF8 support - 33 spare error + 33 [this code is not in use] 34 character value in \ex{...} sequence is too large 35 invalid condition (?(0) 36 \eC not allowed in lookbehind assertion @@ -650,16 +719,33 @@ 39 closing ) for (?C expected 40 recursive call could loop indefinitely 41 unrecognized character after (?P - 42 syntax error after (?P + 42 syntax error in subpattern name (missing terminator) 43 two named subpatterns have the same name 44 invalid UTF-8 string 45 support for \eP, \ep, and \eX has not been compiled 46 malformed \eP or \ep sequence 47 unknown property name after \eP or \ep 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10,000) - 50 repeated subpattern is too long + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] 51 octal value is greater than \e377 (not in UTF-8 mode) + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern not found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \eg is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 (*VERB) with an argument is not supported + 60 (*VERB) not recognized + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode +.sp +The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may +be used if the limits were changed when PCRE was built. . . .SH "STUDYING A PATTERN" @@ -719,19 +805,25 @@ .SH "LOCALE SUPPORT" .rs .sp -PCRE handles caseless matching, and determines whether characters are letters +PCRE handles caseless matching, and determines whether characters are letters, digits, or whatever, by reference to a set of tables, indexed by character value. When running in UTF-8 mode, this applies only to characters with codes less than 128. Higher-valued codes never match escapes such as \ew or \ed, but can be tested with \ep if PCRE is built with Unicode character property -support. The use of locales with Unicode is discouraged. -.P -An internal set of tables is created in the default C locale when PCRE is -built. This is used when the final argument of \fBpcre_compile()\fP is NULL, -and is sufficient for many applications. An alternative set of tables can, -however, be supplied. These may be created in a different locale from the -default. As more and more applications change to using Unicode, the need for -this locale support is expected to die away. +support. The use of locales with Unicode is discouraged. If you are handling +characters with codes greater than 128, you should either use UTF-8 and +Unicode, or use locales, but not try to mix the two. +.P +PCRE contains an internal set of tables that are used when the final argument +of \fBpcre_compile()\fP is NULL. These are sufficient for many applications. +Normally, the internal tables recognize only ASCII characters. However, when +PCRE is built, it is possible to cause the internal tables to be rebuilt in the +default "C" locale of the local system, which may cause them to be different. +.P +The internal tables can always be overridden by tables supplied by the +application that calls PCRE. These may be created in a different locale from +the default. As more and more applications change to using Unicode, the need +for this locale support is expected to die away. .P External tables are built by calling the \fBpcre_maketables()\fP function, which has no arguments, in the relevant locale. The result can then be passed @@ -744,6 +836,9 @@ tables = pcre_maketables(); re = pcre_compile(..., tables); .sp +The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". +.P When \fBpcre_maketables()\fP runs, the tables are built in memory that is obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure that the memory containing the tables remains available for as long as it is @@ -827,7 +922,7 @@ still recognized for backwards compatibility.) .P If there is a fixed first byte, for example, from a pattern such as -(cat|cow|coyote). Otherwise, if either +(cat|cow|coyote), its value is returned. Otherwise, if either .sp (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or @@ -846,6 +941,18 @@ string, a pointer to the table is returned. Otherwise NULL is returned. The fourth argument should point to an \fBunsigned char *\fP variable. .sp + PCRE_INFO_HASCRORLF +.sp +Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The fourth argument should point to an \fBint\fP variable. An +explicit match is either a literal CR or LF character, or \er or \en. +.sp + PCRE_INFO_JCHANGED +.sp +Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The fourth argument should point to an \fBint\fP variable. (?J) and +(?-J) set and unset the local PCRE_DUPNAMES option, respectively. +.sp PCRE_INFO_LASTLITERAL .sp Return the value of the rightmost literal byte that must exist in any matched @@ -882,8 +989,8 @@ PCRE_EXTENDED is set, so white space - including newlines - is ignored): .sp .\" JOIN - (?P<date> (?P<year>(\ed\ed)?\ed\ed) - - (?P<month>\ed\ed) - (?P<day>\ed\ed) ) + (?<date> (?<year>(\ed\ed)?\ed\ed) - + (?<month>\ed\ed) - (?<day>\ed\ed) ) .sp There are four named subpatterns, so the table has four entries, and each entry in the table is eight bytes long. The table is as follows, with non-printing @@ -898,12 +1005,25 @@ name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. .sp + PCRE_INFO_OKPARTIAL +.sp +Return 1 if the pattern can be used for partial matching, otherwise 0. The +fourth argument should point to an \fBint\fP variable. The +.\" HREF +\fBpcrepartial\fP +.\" +documentation lists the restrictions that apply to patterns when partial +matching is used. +.sp PCRE_INFO_OPTIONS .sp Return a copy of the options with which the pattern was compiled. The fourth argument should point to an \fBunsigned long int\fP variable. These option bits are those specified in the call to \fBpcre_compile()\fP, modified by any -top-level option settings within the pattern itself. +top-level option settings at the start of the pattern itself. In other words, +they are the options that will be in force when matching starts. For example, +if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the +result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. .P A pattern is automatically anchored by PCRE if all of its top-level alternatives begin with one of the following: @@ -1114,12 +1234,14 @@ .\" documentation for a discussion of saving compiled patterns for later use. . +.\" HTML <a name="execoptions"></a> .SS "Option bits for \fBpcre_exec()\fP" .rs .sp The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, +PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. .sp PCRE_ANCHORED .sp @@ -1128,14 +1250,47 @@ to be anchored by virtue of its contents, it cannot be made unachored at matching time. .sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +.sp PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY .sp These options override the newline definition that was chosen or defaulted when -the pattern was compiled. For details, see the description \fBpcre_compile()\fP -above. During matching, the newline choice affects the behaviour of the dot, -circumflex, and dollar metacharacters. +the pattern was compiled. For details, see the description of +\fBpcre_compile()\fP above. During matching, the newline choice affects the +behaviour of the dot, circumflex, and dollar metacharacters. It may also alter +the way the match position is advanced after a match failure for an unanchored +pattern. +.P +When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a +match attempt for an unanchored pattern fails when the current position is at a +CRLF sequence, and the pattern contains no explicit matches for CR or LF +characters, the match position is advanced by two characters instead of one, in +other words, to after the CRLF. +.P +The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not +set), it does not match the string "\er\enA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\er\en]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +.P +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \er or \en escape sequences. Implicit matches such as +[^X] do not count, nor does \es (which includes CR and LF in the characters +that it matches). +.P +Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \er or \en escapes appear in the pattern. .sp PCRE_NOTBOL .sp @@ -1173,14 +1328,34 @@ starting offset (see below) and trying an ordinary match again. There is some code that demonstrates how to do this in the \fIpcredemo.c\fP sample program. .sp + PCRE_NO_START_OPTIMIZE +.sp +There are a number of optimizations that \fBpcre_exec()\fP uses at the start of +a match, in order to speed up the process. For example, if it is known that a +match must start with a specific character, it searches the subject for that +character, and fails immediately if it cannot find it, without actually running +the main matching function. When callouts are in use, these optimizations can +cause them to be skipped. This option disables the "start-up" optimizations, +causing performance to suffer, but ensuring that the callouts do occur. +.sp PCRE_NO_UTF8_CHECK .sp When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 string is automatically checked when \fBpcre_exec()\fP is subsequently called. The value of \fIstartoffset\fP is also checked to ensure that it points to the -start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found, -\fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP -contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. +start of a UTF-8 character. There is a discussion about the validity of UTF-8 +strings in the +.\" HTML <a href="pcre.html#utf8strings"> +.\" </a> +section on UTF-8 support +.\" +in the main +.\" HREF +\fBpcre\fP +.\" +page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns +the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value, +PCRE_ERROR_BADUTF8_OFFSET is returned. .P If you already know that your subject is valid, and you want to skip these checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when @@ -1210,11 +1385,11 @@ .rs .sp The subject string is passed to \fBpcre_exec()\fP as a pointer in -\fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in -\fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a -UTF-8 character. Unlike the pattern string, the subject may contain binary zero -bytes. When the starting offset is zero, the search for a match starts at the -beginning of the subject, and this is by far the most common case. +\fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset +in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of +a UTF-8 character. Unlike the pattern string, the subject may contain binary +zero bytes. When the starting offset is zero, the search for a match starts at +the beginning of the subject, and this is by far the most common case. .P A non-zero starting offset is useful when searching for another match in the same subject by calling \fBpcre_exec()\fP again after a previous success. @@ -1248,38 +1423,41 @@ a fragment of a pattern that picks out a substring. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. .P -Captured substrings are returned to the caller via a vector of integer offsets -whose address is passed in \fIovector\fP. The number of elements in the vector -is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: -this argument is NOT the size of \fIovector\fP in bytes. +Captured substrings are returned to the caller via a vector of integers whose +address is passed in \fIovector\fP. The number of elements in the vector is +passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this +argument is NOT the size of \fIovector\fP in bytes. .P The first two-thirds of the vector is used to pass back captured substrings, each substring using a pair of integers. The remaining third of the vector is used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns, -and is not available for passing back information. The length passed in +and is not available for passing back information. The number passed in \fIovecsize\fP should always be a multiple of three. If it is not, it is rounded down. .P When a match is successful, information about captured substrings is returned in pairs of integers, starting at the beginning of \fIovector\fP, and -continuing up to two-thirds of its length at the most. The first element of a -pair is set to the offset of the first character in a substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP -is one more than the highest numbered pair that has been set. For example, if -two substrings have been captured, the returned value is 3. If there are no -capturing subpatterns, the return value from a successful match is 1, -indicating that just the first pair of offsets has been set. +continuing up to two-thirds of its length at the most. The first element of +each pair is set to the byte offset of the first character in a substring, and +the second is set to the byte offset of the first character after the end of a +substring. \fBNote\fP: these values are always byte offsets, even in UTF-8 +mode. They are not character counts. +.P +The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the +portion of the subject string matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +\fBpcre_exec()\fP is one more than the highest numbered pair that has been set. +For example, if two substrings have been captured, the returned value is 3. If +there are no capturing subpatterns, the return value from a successful match is +1, indicating that just the first pair of offsets has been set. .P If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. .P If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the function -returns a value of zero. In particular, if the substring offsets are not of -interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and +returns a value of zero. If the substring offsets are not of interest, +\fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains back references and the \fIovector\fP is not big enough to remember the related substrings, PCRE has to get additional memory for use during matching. Thus it is usually @@ -1336,7 +1514,7 @@ other endianness. This is the error that PCRE gives when the magic number is not present. .sp - PCRE_ERROR_UNKNOWN_NODE (-5) + PCRE_ERROR_UNKNOWN_OPCODE (-5) .sp While running the pattern match, an unknown item was encountered in the compiled pattern. This error could be caused by a bug in PCRE or by overwriting @@ -1362,12 +1540,6 @@ \fBpcre_extra\fP structure (or defaulted) was reached. See the description above. .sp - PCRE_ERROR_RECURSIONLIMIT (-21) -.sp -The internal recursion limit, as specified by the \fImatch_limit_recursion\fP -field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the -description above. -.sp PCRE_ERROR_CALLOUT (-9) .sp This error is never generated by \fBpcre_exec()\fP itself. It is provided for @@ -1411,6 +1583,18 @@ PCRE_ERROR_BADCOUNT (-15) .sp This error is given if the value of the \fIovecsize\fP argument is negative. +.sp + PCRE_ERROR_RECURSIONLIMIT (-21) +.sp +The internal recursion limit, as specified by the \fImatch_limit_recursion\fP +field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the +description above. +.sp + PCRE_ERROR_BADNEWLINE (-23) +.sp +An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given. +.P +Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP. . . .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER" @@ -1422,14 +1606,12 @@ .ti +5n .B int \fIbuffersize\fP); .PP -.br .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, .ti +5n .B int \fIstringcount\fP, int \fIstringnumber\fP, .ti +5n .B const char **\fIstringptr\fP); .PP -.br .B int pcre_get_substring_list(const char *\fIsubject\fP, .ti +5n .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" @@ -1468,7 +1650,7 @@ \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is obtained via \fBpcre_malloc\fP, and its address is returned via \fIstringptr\fP. The yield of the function is the length of the string, not -including the terminating zero, or one of +including the terminating zero, or one of these error codes: .sp PCRE_ERROR_NOMEMORY (-6) .sp @@ -1484,7 +1666,7 @@ memory that is obtained via \fBpcre_malloc\fP. The address of the memory block is returned via \fIlistptr\fP, which is also the start of the list of string pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or +function is zero if all went well, or the error code .sp PCRE_ERROR_NOMEMORY (-6) .sp @@ -1515,7 +1697,6 @@ .ti +5n .B const char *\fIname\fP); .PP -.br .B int pcre_copy_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, @@ -1524,7 +1705,6 @@ .ti +5n .B char *\fIbuffer\fP, int \fIbuffersize\fP); .PP -.br .B int pcre_get_named_substring(const pcre *\fIcode\fP, .ti +5n .B const char *\fIsubject\fP, int *\fIovector\fP, @@ -1536,7 +1716,7 @@ To extract a substring by name, you first have to find associated number. For example, for this pattern .sp - (a+)b(?P<xxx>\ed+)... + (a+)b(?<xxx>\ed+)... .sp the number of the subpattern called "xxx" is 2. If the name is known to be unique (PCRE_DUPNAMES was not set), you can find the number from the name by @@ -1560,9 +1740,14 @@ translation table. .P These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they -then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as -appropriate. -. +then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as +appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names, +the behaviour may not be what you want (see the next section). +.P +\fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple +subpatterns with the same number, you cannot use names to distinguish them, +because names are not included in the compiled code. The matching process uses +only numbers. . .SH "DUPLICATE SUBPATTERN NAMES" .rs @@ -1578,22 +1763,25 @@ .\" HREF \fBpcrepattern\fP .\" -documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP -and \fBpcre_get_named_substring()\fP return the first substring corresponding -to the given name that is set. If none are set, an empty string is returned. -The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are -associated with the name, but it is not defined which it is. -.sp +documentation. +.P +When duplicates are present, \fBpcre_copy_named_substring()\fP and +\fBpcre_get_named_substring()\fP return the first substring corresponding to +the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is +returned; no data is returned. The \fBpcre_get_stringnumber()\fP function +returns one of the numbers that are associated with the name, but it is not +defined which it is. +.P If you want to get full details of all captured substrings for a given name, you must use the \fBpcre_get_stringtable_entries()\fP function. The first argument is the compiled pattern, and the second is the name. The third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the given name. The function itself returns the length of each entry, or -PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described -above in the section entitled \fIInformation about a pattern\fP. Given all the -relevant entries for the name, you can extract each of their numbers, and hence -the captured data, if any. +PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is +described above in the section entitled \fIInformation about a pattern\fP. +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data, if any. . . .SH "FINDING ALL POSSIBLE MATCHES" @@ -1631,11 +1819,12 @@ .B int *\fIworkspace\fP, int \fIwscount\fP); .P The function \fBpcre_dfa_exec()\fP is called to match a subject string against -a compiled pattern, using a "DFA" matching algorithm. This has different -characteristics to the normal algorithm, and is not compatible with Perl. Some -of the features of PCRE patterns are not supported. Nevertheless, there are -times when this kind of matching can be useful. For a discussion of the two -matching algorithms, see the +a compiled pattern, using a matching algorithm that scans the subject string +just once, and does not backtrack. This has different characteristics to the +normal algorithm, and is not compatible with Perl. Some of the features of PCRE +patterns are not supported. Nevertheless, there are times when this kind of +matching can be useful. For a discussion of the two matching algorithms, see +the .\" HREF \fBpcrematching\fP .\" @@ -1691,9 +1880,9 @@ PCRE_DFA_SHORTEST .sp Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as -soon as it has found one match. Because of the way the DFA algorithm works, -this is necessarily the shortest possible match at the first possible matching -point in the subject string. +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. .sp PCRE_DFA_RESTART .sp @@ -1732,10 +1921,10 @@ On success, the yield of the function is a number greater than zero, which is the number of matched substrings. The substrings themselves are returned in \fIovector\fP. Each string uses two elements; the first is the offset to the -start, and the second is the offset to the end. All the strings have the same -start offset. (Space could have been saved by giving this only once, but it was -decided to retain some compatibility with the way \fBpcre_exec()\fP returns -data, even though the meaning of the strings is different.) +start, and the second is the offset to the end. In fact, all the strings have +the same start offset. (Space could have been saved by giving this only once, +but it was decided to retain some compatibility with the way \fBpcre_exec()\fP +returns data, even though the meaning of the strings is different.) .P The strings are returned in reverse order of length; that is, the longest matching string is given first. If there were too many matches to fit into @@ -1762,8 +1951,9 @@ .sp PCRE_ERROR_DFA_UCOND (-17) .sp -This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a -pattern that uses a back reference for the condition. This is not supported. +This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that +uses a back reference for the condition, or a test for recursion in a specific +group. These are not supported. .sp PCRE_ERROR_DFA_UMLIMIT (-18) .sp @@ -1782,8 +1972,30 @@ recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. -.P -.in 0 -Last updated: 08 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3), +\fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3), +\fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 11 April 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrebuild.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrebuild.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrebuild.3 Mon Jun 8 18:51:30 2009 @@ -5,16 +5,21 @@ .rs .sp This document describes the optional features of PCRE that can be selected when -the library is compiled. They are all selected, or deselected, by providing -options to the \fBconfigure\fP script that is run before the \fBmake\fP -command. The complete list of options for \fBconfigure\fP (which includes the -standard ones such as the selection of the installation directory) can be -obtained by running +the library is compiled. It assumes use of the \fBconfigure\fP script, where +the optional features are selected or deselected by providing options to +\fBconfigure\fP before running the \fBmake\fP command. However, the same +options can be selected in both Unix-like and non-Unix-like environments using +the GUI facility of \fBCMakeSetup\fP if you are using \fBCMake\fP instead of +\fBconfigure\fP to build PCRE. +.P +The complete list of options for \fBconfigure\fP (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running .sp ./configure --help .sp -The following sections describe certain options whose names begin with --enable -or --disable. These settings specify changes to the defaults for the +The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the \fBconfigure\fP command. Because of the way that \fBconfigure\fP works, --enable and --disable always come in pairs, so the complementary option always exists as well, but as it specifies the default, it is not described. @@ -33,7 +38,7 @@ .SH "UTF-8 SUPPORT" .rs .sp -To build PCRE with support for UTF-8 character strings, add +To build PCRE with support for UTF-8 Unicode character strings, add .sp --enable-utf8 .sp @@ -41,6 +46,12 @@ strings as UTF-8. As well as compiling PCRE with this option, you also have have to set the PCRE_UTF8 option when you call the \fBpcre_compile()\fP function. +.P +If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE expects +its input to be either ASCII or UTF-8 (depending on the runtime option). It is +not possible to support both EBCDIC and UTF-8 codes in the same version of the +library. Consequently, --enable-utf8 and --enable-ebcdic are mutually +exclusive. . .SH "UNICODE CHARACTER PROPERTY SUPPORT" .rs @@ -56,9 +67,9 @@ to the \fBconfigure\fP command. This implies UTF-8 support, even if you have not explicitly requested it. .P -Including Unicode property support adds around 90K of tables to the PCRE -library, approximately doubling its size. Only the general category properties -such as \fILu\fP and \fINd\fP are supported. Details are given in the +Including Unicode property support adds around 30K of tables to the PCRE +library. Only the general category properties such as \fILu\fP and \fINd\fP are +supported. Details are given in the .\" HREF \fBpcrepattern\fP .\" @@ -67,9 +78,9 @@ .SH "CODE VALUE OF NEWLINE" .rs .sp -By default, PCRE interprets character 10 (linefeed, LF) as indicating the end +By default, PCRE interprets the linefeed (LF) character as indicating the end of a line. This is the normal newline character on Unix-like systems. You can -compile PCRE to use character 13 (carriage return, CR) instead, by adding +compile PCRE to use carriage return (CR) instead, by adding .sp --enable-newline-is-cr .sp @@ -81,9 +92,32 @@ .sp --enable-newline-is-crlf .sp -to the \fBconfigure\fP command. Whatever line ending convention is selected -when PCRE is built can be overridden when the library functions are called. At -build time it is conventional to use the standard for your operating system. +to the \fBconfigure\fP command. There is a fourth option, specified by +.sp + --enable-newline-is-anycrlf +.sp +which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +.sp + --enable-newline-is-any +.sp +causes PCRE to recognize any Unicode newline sequence. +.P +Whatever line ending convention is selected when PCRE is built can be +overridden when the library functions are called. At build time it is +conventional to use the standard for your operating system. +. +.SH "WHAT \eR MATCHES" +.rs +.sp +By default, the sequence \eR in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +.sp + --enable-bsr-anycrlf +.sp +the default is changed so that \eR matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. . .SH "BUILDING SHARED AND STATIC LIBRARIES" .rs @@ -131,10 +165,6 @@ to the \fBconfigure\fP command. The value given must be 2, 3, or 4. Using longer offsets slows down the operation of PCRE because it has to load additional bytes when handling them. -.P -If you build PCRE with an increased link size, test 2 (and test 5 if you are -using UTF-8) will fail. Part of the output of these tests is a representation -of the compiled pattern, and this changes with the link size. . .SH "AVOIDING EXCESSIVE STACK USAGE" .rs @@ -157,13 +187,17 @@ .sp to the \fBconfigure\fP command. With this configuration, PCRE will use the \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP variables to call memory -management functions. Separate functions are provided because the usage is very -predictable: the block sizes requested are always the same, and the blocks are -always freed in reverse order. A calling program might be able to implement -optimized functions that perform better than the standard \fBmalloc()\fP and -\fBfree()\fP functions. PCRE runs noticeably more slowly when built in this -way. This option affects only the \fBpcre_exec()\fP function; it is not -relevant for the the \fBpcre_dfa_exec()\fP function. +management functions. By default these point to \fBmalloc()\fP and +\fBfree()\fP, but you can replace the pointers so that your own functions are +used. +.P +Separate functions are provided rather than using \fBpcre_malloc\fP and +\fBpcre_free\fP because the usage is very predictable: the block sizes +requested are always the same, and the blocks are always freed in reverse +order. A calling program might be able to implement optimized functions that +perform better than \fBmalloc()\fP and \fBfree()\fP. PCRE runs noticeably more +slowly when built in this way. This option affects only the \fBpcre_exec()\fP +function; it is not relevant for the the \fBpcre_dfa_exec()\fP function. . .SH "LIMITING PCRE RESOURCE USAGE" .rs @@ -196,18 +230,105 @@ .sp to the \fBconfigure\fP command. This value can also be overridden at run time. . +.SH "CREATING CHARACTER TABLES AT BUILD TIME" +.rs +.sp +PCRE uses fixed tables for processing characters whose code values are less +than 256. By default, PCRE is built with a set of tables that are distributed +in the file \fIpcre_chartables.c.dist\fP. These tables are for ASCII codes +only. If you add +.sp + --enable-rebuild-chartables +.sp +to the \fBconfigure\fP command, the distributed tables are no longer used. +Instead, a program called \fBdftables\fP is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C runtime +system. (This method of replacing the tables does not work if you are cross +compiling, because \fBdftables\fP is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) +. .SH "USING EBCDIC CODE" .rs .sp PCRE assumes by default that it will run in an environment where the character -code is ASCII (or Unicode, which is a superset of ASCII). PCRE can, however, be -compiled to run in an EBCDIC environment by adding +code is ASCII (or Unicode, which is a superset of ASCII). This is the case for +most computer operating systems. PCRE can, however, be compiled to run in an +EBCDIC environment by adding .sp --enable-ebcdic .sp -to the \fBconfigure\fP command. +to the \fBconfigure\fP command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). The +--enable-ebcdic option is incompatible with --enable-utf8. +. +.SH "PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT" +.rs +.sp +By default, \fBpcregrep\fP reads all files as plain text. You can build it so +that it recognizes files whose names end in \fB.gz\fP or \fB.bz2\fP, and reads +them with \fBlibz\fP or \fBlibbz2\fP, respectively, by adding one or both of +.sp + --enable-pcregrep-libz + --enable-pcregrep-libbz2 +.sp +to the \fBconfigure\fP command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. +. +.SH "PCRETEST OPTION FOR LIBREADLINE SUPPORT" +.rs +.sp +If you add +.sp + --enable-pcretest-libreadline +.sp +to the \fBconfigure\fP command, \fBpcretest\fP is linked with the +\fBlibreadline\fP library, and when its input is from a terminal, it reads it +using the \fBreadline()\fP function. This provides line-editing and history +facilities. Note that \fBlibreadline\fP is GPL-licenced, so if you distribute a +binary of \fBpcretest\fP linked in this way, there may be licensing issues. .P -.in 0 -Last updated: 06 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +Setting this option causes the \fB-lreadline\fP option to be added to the +\fBpcretest\fP build. In many operating environments with a sytem-installed +\fBlibreadline\fP this is sufficient. However, in some environments (e.g. +if an unmodified distribution version of readline is in use), some extra +configuration may be necessary. The INSTALL file for \fBlibreadline\fP says +this: +.sp + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." +.sp +If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +.sp + LIBS="-ncurses" +.sp +immediately before the \fBconfigure\fP command. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcreapi\fP(3), \fBpcre_config\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 17 March 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrecallout.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrecallout.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrecallout.3 Mon Jun 8 18:51:30 2009 @@ -17,7 +17,7 @@ a number less than 256 after the letter C. The default value is zero. For example, this pattern has two callout points: .sp - (?C1)\deabc(?C2)def + (?C1)abc(?C2)def .sp If the PCRE_AUTO_CALLOUT option bit is set when \fBpcre_compile()\fP is called, PCRE automatically inserts callouts, all with number 255, before each item in @@ -44,7 +44,8 @@ .rs .sp You should be aware that, because of optimizations in the way PCRE matches -patterns, callouts sometimes do not happen. For example, if the pattern is +patterns by default, callouts sometimes do not happen. For example, if the +pattern is .sp ab(?C4)cd .sp @@ -52,6 +53,11 @@ string is "abyz", the lack of "d" means that matching doesn't ever start, and the callout is never reached. However, with "abyd", though the result is still no match, the callout is obeyed. +.P +You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE +option to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. This slows down the +matching process, but does ensure that callouts such as the example above are +obeyed. . . .SH "THE CALLOUT INTERFACE" @@ -95,10 +101,12 @@ The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values that were passed to \fBpcre_exec()\fP. .P -The \fIstart_match\fP field contains the offset within the subject at which the -current match attempt started. If the pattern is not anchored, the callout -function may be called several times from the same point in the pattern for -different starting points in the subject. +The \fIstart_match\fP field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \eK +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. .P The \fIcurrent_position\fP field contains the offset within the subject of the current match pointer. @@ -154,8 +162,22 @@ values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; it will never be used by PCRE itself. -.P -.in 0 -Last updated: 28 February 2005 -.br -Copyright (c) 1997-2005 University of Cambridge. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 15 March 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrecompat.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrecompat.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrecompat.3 Mon Jun 8 18:51:30 2009 @@ -5,8 +5,9 @@ .rs .sp This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are with respect to Perl -5.8. +regular expressions. The differences described here are mainly with respect to +Perl 5.8, though PCRE versions 7.0 and later contain some features that are +expected to be in the forthcoming Perl 5.10. .P 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what it does have are given in the @@ -63,20 +64,32 @@ .sp The \eQ...\eE sequence is recognized both inside and outside character classes. .P -8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) -constructions. However, there is support for recursive patterns using the -non-Perl items (?R), (?number), and (?P>name). Also, the PCRE "callout" feature -allows an external function to be called during pattern matching. See the +8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE "callout" +feature allows an external function to be called during pattern matching. See +the .\" HREF \fBpcrecallout\fP .\" documentation for details. .P -9. There are some differences that are concerned with the settings of captured +9. Subpatterns that are called recursively or as "subroutines" are always +treated as atomic groups in PCRE. This is like Python, but unlike Perl. +.P +10. There are some differences that are concerned with the settings of captured strings when part of a pattern is repeated. For example, matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". .P -10. PCRE provides some extensions to the Perl regular expression facilities: +11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), (*FAIL), (*F), +(*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in the forms without an +argument. PCRE does not support (*MARK). If (*ACCEPT) is within capturing +parentheses, PCRE does not set that capture group; this is different to Perl. +.P +12. PCRE provides some extensions to the Perl regular expression facilities. +Perl 5.10 will include new features that are not in earlier versions, some of +which (such as named parentheses) have been in PCRE for some time. This list is +with respect to Perl 5.10: .sp (a) Although lookbehind assertions must match fixed length strings, each alternative branch of a lookbehind assertion can match a different length of @@ -86,8 +99,8 @@ meta-character matches only at the very end of the string. .sp (c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. Otherwise, like Perl, the backslash is ignored. (Perl can -be made to issue a warning.) +meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. +(Perl can be made to issue a warning.) .sp (d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is inverted, that is, by default they are not greedy, but if followed by a @@ -99,28 +112,37 @@ (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE options for \fBpcre_exec()\fP have no Perl equivalents. .sp -(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern -matching (Perl can do this using the (?p{code}) construct, which PCRE cannot -support.) +(g) The \eR escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. .sp -(h) PCRE supports named capturing substrings, using the Python syntax. +(h) The callout facility is PCRE-specific. .sp -(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java -package. +(i) The partial matching facility is PCRE-specific. .sp -(j) The (R) condition, for testing recursion, is a PCRE extension. +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. .sp -(k) The callout facility is PCRE-specific. +(k) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a +different way and is not Perl-compatible. .sp -(l) The partial matching facility is PCRE-specific. +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. +. +. +.SH AUTHOR +.rs .sp -(m) Patterns compiled by PCRE can be saved and re-used at a later time, even on -different hosts that have the other endianness. +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs .sp -(n) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a -different way and is not Perl-compatible. -.P -.in 0 -Last updated: 06 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +.nf +Last updated: 11 September 2007 +Copyright (c) 1997-2007 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrecpp.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrecpp.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrecpp.3 Mon Jun 8 18:51:30 2009 @@ -5,9 +5,7 @@ .rs .sp .B #include <pcrecpp.h> -.PP -.SM -.br +. .SH DESCRIPTION .rs .sp @@ -81,14 +79,42 @@ .sp c. The "i"th argument has a suitable type for holding the string captured as the "i"th sub-pattern. If you pass in - NULL for the "i"th argument, or pass fewer arguments than + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the number of sub-patterns, "i"th captured sub-pattern is ignored. .sp +CAVEAT: An optional sub-pattern that does not exist in the matched +string is assigned the empty string. Therefore, the following will +return false (because the empty string is not a valid number): +.sp + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\e\ed+)?", &number); +.sp The matching interface supports at most 16 arguments per call. If you need more, consider using the more general interface \fBpcrecpp::RE::DoMatch\fP. See \fBpcrecpp.h\fP for the signature for \fBDoMatch\fP. +.P +NOTE: Do not use \fBno_arg\fP, which is used internally to mark the end of a +list of optional arguments, as a placeholder for missing arguments, as this can +lead to segfaults. +. +. +.SH "QUOTING METACHARACTERS" +.rs +.sp +You can use the "QuoteMeta" operation to insert backslashes before all +potentially meaningful characters in a string. The returned string, used as a +regular expression, will exactly match the original string. +.sp + Example: + string quoted = RE::QuoteMeta(unquoted); +.sp +Note that it's legal to escape a character even if it has no special meaning in +a regular expression -- so this function does that. (This also makes it +identical to the perl function of the same name; see "perldoc -f quotemeta".) +For example, "1.5-2.0?" becomes "1\e.5\e-2\e.0\e?". . .SH "PARTIAL MATCHES" .rs @@ -307,6 +333,15 @@ .SH AUTHOR .rs .sp +.nf The C++ wrapper was contributed by Google Inc. -.br -Copyright (c) 2005 Google Inc. +Copyright (c) 2007 Google Inc. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 17 March 2009 +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcregrep.1 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcregrep.1 (original) +++ freeswitch/trunk/libs/pcre/doc/pcregrep.1 Mon Jun 8 18:51:30 2009 @@ -11,10 +11,10 @@ grep commands do, but it uses the PCRE regular expression library to support patterns that are compatible with the regular expressions of Perl 5. See .\" HREF -\fBpcrepattern\fP +\fBpcrepattern\fP(3) .\" -for a full description of syntax and semantics of the regular expressions that -PCRE supports. +for a full description of syntax and semantics of the regular expressions +that PCRE supports. .P Patterns, whether supplied on the command line or in a separate file, are given without delimiters. For example: @@ -23,9 +23,9 @@ .sp If you attempt to use delimiters (for example, by surrounding a pattern with slashes, as is common in Perl scripts), they are interpreted as part of the -pattern. Quotes can of course be used on the command line because they are -interpreted by the shell, and indeed they are required if a pattern contains -white space or shell metacharacters. +pattern. Quotes can of course be used to delimit patterns on the command line +because they are interpreted by the shell, and indeed they are required if a +pattern contains white space or shell metacharacters. .P The first argument that follows any option settings is treated as the single pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present. @@ -39,20 +39,53 @@ .sp pcregrep some-pattern /file1 - /file3 .sp -By default, each line that matches the pattern is copied to the standard +By default, each line that matches a pattern is copied to the standard output, and if there is more than one file, the file name is output at the -start of each line. However, there are options that can change how -\fBpcregrep\fP behaves. In particular, the \fB-M\fP option makes it possible to -search for patterns that span line boundaries. What defines a line boundary is -controlled by the \fB-N\fP (\fB--newline\fP) option. +start of each line, followed by a colon. However, there are options that can +change how \fBpcregrep\fP behaves. In particular, the \fB-M\fP option makes it +possible to search for patterns that span line boundaries. What defines a line +boundary is controlled by the \fB-N\fP (\fB--newline\fP) option. .P Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. -BUFSIZ is defined in \fB<stdio.h>\fP. +BUFSIZ is defined in \fB<stdio.h>\fP. When there is more than one pattern +(specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to +each line in the order in which they are defined, except that all the \fB-e\fP +patterns are tried before the \fB-f\fP patterns. +.P +By default, as soon as one pattern matches (or fails to match when \fB-v\fP is +used), no further patterns are considered. However, if \fB--colour\fP (or +\fB--color\fP) is used to colour the matching substrings, or if +\fB--only-matching\fP, \fB--file-offsets\fP, or \fB--line-offsets\fP is used to +output only the part of the line that matched (either shown literally, or as an +offset), scanning resumes immediately following the match, so that further +matches on the same line can be found. If there are multiple patterns, they are +all tried on the remainder of the line, but patterns that follow the one that +matched are not tried on the earlier part of the line. +.P +This is the same behaviour as GNU grep, but it does mean that the order in +which multiple patterns are specified can affect the output when one of the +above options is used. +.P +Patterns that can match an empty string are accepted, but empty string +matches are not recognized. An example is the pattern "(super)?(man)?", in +which all components are optional. This pattern finds all occurrences of both +"super" and "man"; the output differs from matching with "super|man" when only +the matching substrings are being shown. .P If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set, \fBpcregrep\fP uses the value to set a locale when calling the PCRE library. The \fB--locale\fP option can be used to override this. . +.SH "SUPPORT FOR COMPRESSED FILES" +.rs +.sp +It is possible to compile \fBpcregrep\fP so that it uses \fBlibz\fP or +\fBlibbz2\fP to read files whose names end in \fB.gz\fP or \fB.bz2\fP, +respectively. You can find out whether your binary has support for one or both +of these file types by running it with the \fB--help\fP option. If the +appropriate support is not present, files are treated as plain text. The +standard input is always so treated. +. .SH OPTIONS .rs .TP 10 @@ -93,16 +126,20 @@ equals sign. .TP \fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP -This option specifies under what circumstances the part of a line that matched -a pattern should be coloured in the output. The value may be "never" (the -default), "always", or "auto". In the latter case, colouring happens only if -the standard output is connected to a terminal. The colour can be specified by -setting the environment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value -of this variable should be a string of two numbers, separated by a semicolon. -They are copied directly into the control string for setting colour on a -terminal, so it is your responsibility to ensure that they make sense. If -neither of the environment variables is set, the default is "1;31", which gives -red. +This option specifies under what circumstances the parts of a line that matched +a pattern should be coloured in the output. By default, the output is not +coloured. The value (which is optional, see above) may be "never", "always", or +"auto". In the latter case, colouring happens only if the standard output is +connected to a terminal. More resources are used when colouring is enabled, +because \fBpcregrep\fP has to search for all possible matches in a line, not +just one, in order to colour them all. + +The colour that is used can be specified by setting the environment variable +PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a +string of two numbers, separated by a semicolon. They are copied directly into +the control string for setting colour on a terminal, so it is your +responsibility to ensure that they make sense. If neither of the environment +variables is set, the default is "1;31", which gives red. .TP \fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP If an input path is not a regular file or a directory, "action" specifies how @@ -116,29 +153,41 @@ are read as if they were ordinary files. In some operating systems the effect of reading a directory like this is an immediate end-of-file. .TP -\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, -\fB--regexp=\fP\fIpattern\fP Specify a pattern to be matched. This option can -be used multiple times in order to specify several patterns. It can also be -used as a way of specifying a single pattern that starts with a hyphen. When -\fB-e\fP is used, no argument pattern is taken from the command line; all -arguments are treated as file names. There is an overall maximum of 100 -patterns. They are applied to each line in the order in which they are defined -until one matches (or fails to match if \fB-v\fP is used). If \fB-f\fP is used -with \fB-e\fP, the command line patterns are matched first, followed by the -patterns from the file, independent of the order in which these options are -specified. Note that multiple use of \fB-e\fP is not the same as a single -pattern with alternatives. For example, X|Y finds the first character in a line -that is X or Y, whereas if the two patterns are given separately, -\fBpcregrep\fP finds X if it is present, even if it follows Y in the line. It -finds Y only if there is no X in the line. This really matters only if you are -using \fB-o\fP to show the portion of the line that matched. +\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP +Specify a pattern to be matched. This option can be used multiple times in +order to specify several patterns. It can also be used as a way of specifying a +single pattern that starts with a hyphen. When \fB-e\fP is used, no argument +pattern is taken from the command line; all arguments are treated as file +names. There is an overall maximum of 100 patterns. They are applied to each +line in the order in which they are defined until one matches (or fails to +match if \fB-v\fP is used). If \fB-f\fP is used with \fB-e\fP, the command line +patterns are matched first, followed by the patterns from the file, independent +of the order in which these options are specified. Note that multiple use of +\fB-e\fP is not the same as a single pattern with alternatives. For example, +X|Y finds the first character in a line that is X or Y, whereas if the two +patterns are given separately, \fBpcregrep\fP finds X if it is present, even if +it follows Y in the line. It finds Y only if there is no X in the line. This +really matters only if you are using \fB-o\fP to show the part(s) of the line +that matched. .TP \fB--exclude\fP=\fIpattern\fP When \fBpcregrep\fP is searching the files in a directory as a consequence of -the \fB-r\fP (recursive search) option, any files whose names match the pattern -are excluded. The pattern is a PCRE regular expression. If a file name matches -both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no short -form for this option. +the \fB-r\fP (recursive search) option, any regular files whose names match the +pattern are excluded. Subdirectories are not excluded by this option; they are +searched recursively, subject to the \fB--exclude_dir\fP and +\fB--include_dir\fP options. The pattern is a PCRE regular expression, and is +matched against the final component of the file name (not the entire path). If +a file name matches both \fB--include\fP and \fB--exclude\fP, it is excluded. +There is no short form for this option. +.TP +\fB--exclude_dir\fP=\fIpattern\fP +When \fBpcregrep\fP is searching the contents of a directory as a consequence +of the \fB-r\fP (recursive search) option, any subdirectories whose names match +the pattern are excluded. (Note that the \fP--exclude\fP option does not affect +subdirectories.) The pattern is a PCRE regular expression, and is matched +against the final component of the name (not the entire path). If a +subdirectory name matches both \fB--include_dir\fP and \fB--exclude_dir\fP, it +is excluded. There is no short form for this option. .TP \fB-F\fP, \fB--fixed-strings\fP Interpret each pattern as a list of fixed strings, separated by newlines, @@ -156,34 +205,55 @@ is taken from the command line; all arguments are treated as file names. There is an overall maximum of 100 patterns. Trailing white space is removed from each line, and blank lines are ignored. An empty file contains no patterns and -therefore matches nothing. +therefore matches nothing. See also the comments about multiple patterns versus +a single pattern with alternatives in the description of \fB-e\fP above. +.TP +\fB--file-offsets\fP +Instead of showing lines or parts of lines that match, show each match as an +offset from the start of the file and a length, separated by a comma. In this +mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP +options are ignored. If there is more than one match in a line, each of them is +shown separately. This option is mutually exclusive with \fB--line-offsets\fP +and \fB--only-matching\fP. .TP \fB-H\fP, \fB--with-filename\fP Force the inclusion of the filename at the start of output lines when searching a single file. By default, the filename is not shown in this case. For matching -lines, the filename is followed by a colon and a space; for context lines, a -hyphen separator is used. If a line number is also being output, it follows the -file name without a space. +lines, the filename is followed by a colon; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name. .TP \fB-h\fP, \fB--no-filename\fP Suppress the output filenames when searching multiple files. By default, filenames are shown when multiple files are searched. For matching lines, the -filename is followed by a colon and a space; for context lines, a hyphen -separator is used. If a line number is also being output, it follows the file -name without a space. +filename is followed by a colon; for context lines, a hyphen separator is used. +If a line number is also being output, it follows the file name. .TP \fB--help\fP -Output a brief help message and exit. +Output a help message, giving brief details of the command options and file +type support, and then exit. .TP \fB-i\fP, \fB--ignore-case\fP Ignore upper/lower case distinctions during comparisons. .TP \fB--include\fP=\fIpattern\fP When \fBpcregrep\fP is searching the files in a directory as a consequence of -the \fB-r\fP (recursive search) option, only those files whose names match the -pattern are included. The pattern is a PCRE regular expression. If a file name -matches both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no -short form for this option. +the \fB-r\fP (recursive search) option, only those regular files whose names +match the pattern are included. Subdirectories are always included and searched +recursively, subject to the \fP--include_dir\fP and \fB--exclude_dir\fP +options. The pattern is a PCRE regular expression, and is matched against the +final component of the file name (not the entire path). If a file name matches +both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no short +form for this option. +.TP +\fB--include_dir\fP=\fIpattern\fP +When \fBpcregrep\fP is searching the contents of a directory as a consequence +of the \fB-r\fP (recursive search) option, only those subdirectories whose +names match the pattern are included. (Note that the \fB--include\fP option +does not affect subdirectories.) The pattern is a PCRE regular expression, and +is matched against the final component of the name (not the entire path). If a +subdirectory name matches both \fB--include_dir\fP and \fB--exclude_dir\fP, it +is excluded. There is no short form for this option. .TP \fB-L\fP, \fB--files-without-match\fP Instead of outputting lines from the files, just output the names of the files @@ -201,6 +271,15 @@ are being output. If not supplied, "(standard input)" is used. There is no short form for this option. .TP +\fB--line-offsets\fP +Instead of showing lines or parts of lines that match, show each match as a +line number, the offset from the start of the line, and a length. The line +number is terminated by a colon (as usual; see the \fB-n\fP option), and the +offset and length are separated by a comma. In this mode, no context is shown. +That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is +more than one match in a line, each of them is shown separately. This option is +mutually exclusive with \fB--file-offsets\fP and \fB--only-matching\fP. +.TP \fB--locale\fP=\fIlocale-name\fP This option specifies a locale to be used for pattern matching. It overrides the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no @@ -220,26 +299,38 @@ are guaranteed to be available for lookbehind assertions. .TP \fB-N\fP \fInewline-type\fP, \fB--newline=\fP\fInewline-type\fP -The PCRE library supports three different character sequences for indicating +The PCRE library supports five different conventions for indicating the ends of lines. They are the single-character sequences CR (carriage return) -and LF (linefeed), and the two-character sequence CR, LF. When the library is -built, a default line-ending sequence is specified. This is normally the -standard sequence for the operating system. Unless otherwise specified by this -option, \fBpcregrep\fP uses the default. The possible values for this option -are CR, LF, or CRLF. This makes it possible to use \fBpcregrep\fP on files that -have come from other environments without having to modify their line endings. -If the data that is being scanned does not agree with the convention set by -this option, \fBpcregrep\fP may behave in strange ways. +and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, +which recognizes any of the preceding three types, and an "any" convention, in +which any Unicode line ending sequence is assumed to end a line. The Unicode +sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF +(formfeed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and +PS (paragraph separator, U+2029). +.sp +When the PCRE library is built, a default line-ending sequence is specified. +This is normally the standard sequence for the operating system. Unless +otherwise specified by this option, \fBpcregrep\fP uses the library's default. +The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This +makes it possible to use \fBpcregrep\fP on files that have come from other +environments without having to modify their line endings. If the data that is +being scanned does not agree with the convention set by this option, +\fBpcregrep\fP may behave in strange ways. .TP \fB-n\fP, \fB--line-number\fP Precede each output line by its line number in the file, followed by a colon -and a space for matching lines or a hyphen and a space for context lines. If -the filename is also being output, it precedes the line number. +for matching lines or a hyphen for context lines. If the filename is also being +output, it precedes the line number. This option is forced if +\fB--line-offsets\fP is used. .TP \fB-o\fP, \fB--only-matching\fP Show only the part of the line that matched a pattern. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are -ignored. +ignored. If there is more than one match in a line, each of them is shown +separately. If \fB-o\fP is combined with \fB-v\fP (invert the sense of the +match to find non-matching lines), no output is generated, but the return code +is set appropriately. This option is mutually exclusive with +\fB--file-offsets\fP and \fB--line-offsets\fP. .TP \fB-q\fP, \fB--quiet\fP Work quietly, that is, display nothing except error messages. The exit @@ -274,7 +365,7 @@ Force the patterns to match only whole words. This is equivalent to having \eb at the start and end of the pattern. .TP -\fB-x\fP, \fB--line-regex\fP, \fP--line-regexp\fP +\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP Force the patterns to be anchored (each must start matching at the beginning of a line) and in addition, require them to match entire lines. This is equivalent to having ^ and $ characters at the start and end of each @@ -339,7 +430,7 @@ it has no data. . . -.SH MATCHING ERRORS +.SH "MATCHING ERRORS" .rs .sp It is possible to supply a regular expression that takes a very long time to @@ -361,16 +452,26 @@ code. . . +.SH "SEE ALSO" +.rs +.sp +\fBpcrepattern\fP(3), \fBpcretest\fP(1). +. +. .SH AUTHOR .rs .sp +.nf Philip Hazel -.br University Computing Service -.br -Cambridge CB2 3QG, England. -.P -.in 0 -Last updated: 06 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 01 March 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcregrep.txt ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcregrep.txt (original) +++ freeswitch/trunk/libs/pcre/doc/pcregrep.txt Mon Jun 8 18:51:30 2009 @@ -14,8 +14,8 @@ pcregrep searches files for character patterns, in the same way as other grep commands do, but it uses the PCRE regular expression library to support patterns that are compatible with the regular expressions of - Perl 5. See pcrepattern for a full description of syntax and semantics - of the regular expressions that PCRE supports. + Perl 5. See pcrepattern(3) for a full description of syntax and seman- + tics of the regular expressions that PCRE supports. Patterns, whether supplied on the command line or in a separate file, are given without delimiters. For example: @@ -24,37 +24,72 @@ If you attempt to use delimiters (for example, by surrounding a pattern with slashes, as is common in Perl scripts), they are interpreted as - part of the pattern. Quotes can of course be used on the command line - because they are interpreted by the shell, and indeed they are required - if a pattern contains white space or shell metacharacters. - - The first argument that follows any option settings is treated as the - single pattern to be matched when neither -e nor -f is present. Con- - versely, when one or both of these options are used to specify pat- + part of the pattern. Quotes can of course be used to delimit patterns + on the command line because they are interpreted by the shell, and + indeed they are required if a pattern contains white space or shell + metacharacters. + + The first argument that follows any option settings is treated as the + single pattern to be matched when neither -e nor -f is present. Con- + versely, when one or both of these options are used to specify pat- terns, all arguments are treated as path names. At least one of -e, -f, or an argument pattern must be provided. If no files are specified, pcregrep reads the standard input. The stan- - dard input can also be referenced by a name consisting of a single + dard input can also be referenced by a name consisting of a single hyphen. For example: pcregrep some-pattern /file1 - /file3 - By default, each line that matches the pattern is copied to the stan- - dard output, and if there is more than one file, the file name is out- - put at the start of each line. However, there are options that can - change how pcregrep behaves. In particular, the -M option makes it pos- - sible to search for patterns that span line boundaries. What defines a - line boundary is controlled by the -N (--newline) option. + By default, each line that matches a pattern is copied to the standard + output, and if there is more than one file, the file name is output at + the start of each line, followed by a colon. However, there are options + that can change how pcregrep behaves. In particular, the -M option + makes it possible to search for patterns that span line boundaries. + What defines a line boundary is controlled by the -N (--newline) + option. Patterns are limited to 8K or BUFSIZ characters, whichever is the - greater. BUFSIZ is defined in <stdio.h>. + greater. BUFSIZ is defined in <stdio.h>. When there is more than one + pattern (specified by the use of -e and/or -f), each pattern is applied + to each line in the order in which they are defined, except that all + the -e patterns are tried before the -f patterns. + + By default, as soon as one pattern matches (or fails to match when -v + is used), no further patterns are considered. However, if --colour (or + --color) is used to colour the matching substrings, or if --only-match- + ing, --file-offsets, or --line-offsets is used to output only the part + of the line that matched (either shown literally, or as an offset), + scanning resumes immediately following the match, so that further + matches on the same line can be found. If there are multiple patterns, + they are all tried on the remainder of the line, but patterns that fol- + low the one that matched are not tried on the earlier part of the line. + + This is the same behaviour as GNU grep, but it does mean that the order + in which multiple patterns are specified can affect the output when one + of the above options is used. + + Patterns that can match an empty string are accepted, but empty string + matches are not recognized. An example is the pattern "(super)?(man)?", + in which all components are optional. This pattern finds all occur- + rences of both "super" and "man"; the output differs from matching with + "super|man" when only the matching substrings are being shown. - If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses - the value to set a locale when calling the PCRE library. The --locale + If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses + the value to set a locale when calling the PCRE library. The --locale option can be used to override this. +SUPPORT FOR COMPRESSED FILES + + It is possible to compile pcregrep so that it uses libz or libbz2 to + read files whose names end in .gz or .bz2, respectively. You can find + out whether your binary has support for one or both of these file types + by running it with the --help option. If the appropriate support is not + present, files are treated as plain text. The standard input is always + so treated. + + OPTIONS -- This terminate the list of options. It is useful if the next @@ -99,110 +134,156 @@ the same shell item, separated by an equals sign. --colour=value, --color=value - This option specifies under what circumstances the part of a + This option specifies under what circumstances the parts of a line that matched a pattern should be coloured in the output. - The value may be "never" (the default), "always", or "auto". - In the latter case, colouring happens only if the standard - output is connected to a terminal. The colour can be speci- - fied by setting the environment variable PCREGREP_COLOUR or - PCREGREP_COLOR. The value of this variable should be a string - of two numbers, separated by a semicolon. They are copied - directly into the control string for setting colour on a ter- - minal, so it is your responsibility to ensure that they make - sense. If neither of the environment variables is set, the - default is "1;31", which gives red. + By default, the output is not coloured. The value (which is + optional, see above) may be "never", "always", or "auto". In + the latter case, colouring happens only if the standard out- + put is connected to a terminal. More resources are used when + colouring is enabled, because pcregrep has to search for all + possible matches in a line, not just one, in order to colour + them all. + + The colour that is used can be specified by setting the envi- + ronment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value + of this variable should be a string of two numbers, separated + by a semicolon. They are copied directly into the control + string for setting colour on a terminal, so it is your + responsibility to ensure that they make sense. If neither of + the environment variables is set, the default is "1;31", + which gives red. -D action, --devices=action If an input path is not a regular file or a directory, "action" specifies how it is to be processed. Valid values - are "read" (the default) or "skip" (silently skip the path). + are "read" (the default) or "skip" (silently skip the path). -d action, --directories=action If an input path is a directory, "action" specifies how it is - to be processed. Valid values are "read" (the default), - "recurse" (equivalent to the -r option), or "skip" (silently - skip the path). In the default case, directories are read as - if they were ordinary files. In some operating systems the - effect of reading a directory like this is an immediate end- + to be processed. Valid values are "read" (the default), + "recurse" (equivalent to the -r option), or "skip" (silently + skip the path). In the default case, directories are read as + if they were ordinary files. In some operating systems the + effect of reading a directory like this is an immediate end- of-file. - -e pattern, --regex=pattern, - --regexp=pattern Specify a pattern to be matched. This option - can be used multiple times in order to specify several pat- - terns. It can also be used as a way of specifying a single - pattern that starts with a hyphen. When -e is used, no argu- - ment pattern is taken from the command line; all arguments - are treated as file names. There is an overall maximum of 100 - patterns. They are applied to each line in the order in which - they are defined until one matches (or fails to match if -v - is used). If -f is used with -e, the command line patterns - are matched first, followed by the patterns from the file, - independent of the order in which these options are speci- - fied. Note that multiple use of -e is not the same as a sin- - gle pattern with alternatives. For example, X|Y finds the - first character in a line that is X or Y, whereas if the two - patterns are given separately, pcregrep finds X if it is - present, even if it follows Y in the line. It finds Y only if - there is no X in the line. This really matters only if you - are using -o to show the portion of the line that matched. + -e pattern, --regex=pattern, --regexp=pattern + Specify a pattern to be matched. This option can be used mul- + tiple times in order to specify several patterns. It can also + be used as a way of specifying a single pattern that starts + with a hyphen. When -e is used, no argument pattern is taken + from the command line; all arguments are treated as file + names. There is an overall maximum of 100 patterns. They are + applied to each line in the order in which they are defined + until one matches (or fails to match if -v is used). If -f is + used with -e, the command line patterns are matched first, + followed by the patterns from the file, independent of the + order in which these options are specified. Note that multi- + ple use of -e is not the same as a single pattern with alter- + natives. For example, X|Y finds the first character in a line + that is X or Y, whereas if the two patterns are given sepa- + rately, pcregrep finds X if it is present, even if it follows + Y in the line. It finds Y only if there is no X in the line. + This really matters only if you are using -o to show the + part(s) of the line that matched. --exclude=pattern When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, any files whose - names match the pattern are excluded. The pattern is a PCRE - regular expression. If a file name matches both --include and - --exclude, it is excluded. There is no short form for this + sequence of the -r (recursive search) option, any regular + files whose names match the pattern are excluded. Subdirecto- + ries are not excluded by this option; they are searched + recursively, subject to the --exclude_dir and --include_dir + options. The pattern is a PCRE regular expression, and is + matched against the final component of the file name (not the + entire path). If a file name matches both --include and + --exclude, it is excluded. There is no short form for this option. + --exclude_dir=pattern + When pcregrep is searching the contents of a directory as a + consequence of the -r (recursive search) option, any subdi- + rectories whose names match the pattern are excluded. (Note + that the --exclude option does not affect subdirectories.) + The pattern is a PCRE regular expression, and is matched + against the final component of the name (not the entire + path). If a subdirectory name matches both --include_dir and + --exclude_dir, it is excluded. There is no short form for + this option. + -F, --fixed-strings - Interpret each pattern as a list of fixed strings, separated - by newlines, instead of as a regular expression. The -w - (match as a word) and -x (match whole line) options can be + Interpret each pattern as a list of fixed strings, separated + by newlines, instead of as a regular expression. The -w + (match as a word) and -x (match whole line) options can be used with -F. They apply to each of the fixed strings. A line is selected if any of the fixed strings are found in it (sub- ject to -w or -x, if present). -f filename, --file=filename - Read a number of patterns from the file, one per line, and - match them against each line of input. A data line is output + Read a number of patterns from the file, one per line, and + match them against each line of input. A data line is output if any of the patterns match it. The filename can be given as "-" to refer to the standard input. When -f is used, patterns - specified on the command line using -e may also be present; + specified on the command line using -e may also be present; they are tested before the file's patterns. However, no other - pattern is taken from the command line; all arguments are - treated as file names. There is an overall maximum of 100 + pattern is taken from the command line; all arguments are + treated as file names. There is an overall maximum of 100 patterns. Trailing white space is removed from each line, and - blank lines are ignored. An empty file contains no patterns - and therefore matches nothing. + blank lines are ignored. An empty file contains no patterns + and therefore matches nothing. See also the comments about + multiple patterns versus a single pattern with alternatives + in the description of -e above. + + --file-offsets + Instead of showing lines or parts of lines that match, show + each match as an offset from the start of the file and a + length, separated by a comma. In this mode, no context is + shown. That is, the -A, -B, and -C options are ignored. If + there is more than one match in a line, each of them is shown + separately. This option is mutually exclusive with --line- + offsets and --only-matching. -H, --with-filename - Force the inclusion of the filename at the start of output - lines when searching a single file. By default, the filename - is not shown in this case. For matching lines, the filename - is followed by a colon and a space; for context lines, a - hyphen separator is used. If a line number is also being out- - put, it follows the file name without a space. + Force the inclusion of the filename at the start of output + lines when searching a single file. By default, the filename + is not shown in this case. For matching lines, the filename + is followed by a colon; for context lines, a hyphen separator + is used. If a line number is also being output, it follows + the file name. -h, --no-filename - Suppress the output filenames when searching multiple files. - By default, filenames are shown when multiple files are - searched. For matching lines, the filename is followed by a - colon and a space; for context lines, a hyphen separator is - used. If a line number is also being output, it follows the - file name without a space. + Suppress the output filenames when searching multiple files. + By default, filenames are shown when multiple files are + searched. For matching lines, the filename is followed by a + colon; for context lines, a hyphen separator is used. If a + line number is also being output, it follows the file name. - --help Output a brief help message and exit. + --help Output a help message, giving brief details of the command + options and file type support, and then exit. -i, --ignore-case Ignore upper/lower case distinctions during comparisons. --include=pattern When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, only those - files whose names match the pattern are included. The pattern - is a PCRE regular expression. If a file name matches both - --include and --exclude, it is excluded. There is no short - form for this option. + sequence of the -r (recursive search) option, only those reg- + ular files whose names match the pattern are included. Subdi- + rectories are always included and searched recursively, sub- + ject to the --include_dir and --exclude_dir options. The pat- + tern is a PCRE regular expression, and is matched against the + final component of the file name (not the entire path). If a + file name matches both --include and --exclude, it is + excluded. There is no short form for this option. + + --include_dir=pattern + When pcregrep is searching the contents of a directory as a + consequence of the -r (recursive search) option, only those + subdirectories whose names match the pattern are included. + (Note that the --include option does not affect subdirecto- + ries.) The pattern is a PCRE regular expression, and is + matched against the final component of the name (not the + entire path). If a subdirectory name matches both + --include_dir and --exclude_dir, it is excluded. There is no + short form for this option. -L, --files-without-match Instead of outputting lines from the files, just output the @@ -222,6 +303,17 @@ when file names are being output. If not supplied, "(standard input)" is used. There is no short form for this option. + --line-offsets + Instead of showing lines or parts of lines that match, show + each match as a line number, the offset from the start of the + line, and a length. The line number is terminated by a colon + (as usual; see the -n option), and the offset and length are + separated by a comma. In this mode, no context is shown. + That is, the -A, -B, and -C options are ignored. If there is + more than one match in a line, each of them is shown sepa- + rately. This option is mutually exclusive with --file-offsets + and --only-matching. + --locale=locale-name This option specifies a locale to be used for pattern match- ing. It overrides the value in the LC_ALL or LC_CTYPE envi- @@ -245,60 +337,73 @@ lookbehind assertions. -N newline-type, --newline=newline-type - The PCRE library supports three different character sequences - for indicating the ends of lines. They are the single-charac- - ter sequences CR (carriage return) and LF (linefeed), and the - two-character sequence CR, LF. When the library is built, a - default line-ending sequence is specified. This is normally - the standard sequence for the operating system. Unless other- - wise specified by this option, pcregrep uses the default. The - possible values for this option are CR, LF, or CRLF. This - makes it possible to use pcregrep on files that have come - from other environments without having to modify their line - endings. If the data that is being scanned does not agree - with the convention set by this option, pcregrep may behave - in strange ways. + The PCRE library supports five different conventions for + indicating the ends of lines. They are the single-character + sequences CR (carriage return) and LF (linefeed), the two- + character sequence CRLF, an "anycrlf" convention, which rec- + ognizes any of the preceding three types, and an "any" con- + vention, in which any Unicode line ending sequence is assumed + to end a line. The Unicode sequences are the three just men- + tioned, plus VT (vertical tab, U+000B), FF (formfeed, + U+000C), NEL (next line, U+0085), LS (line separator, + U+2028), and PS (paragraph separator, U+2029). + + When the PCRE library is built, a default line-ending + sequence is specified. This is normally the standard + sequence for the operating system. Unless otherwise specified + by this option, pcregrep uses the library's default. The + possible values for this option are CR, LF, CRLF, ANYCRLF, or + ANY. This makes it possible to use pcregrep on files that + have come from other environments without having to modify + their line endings. If the data that is being scanned does + not agree with the convention set by this option, pcregrep + may behave in strange ways. -n, --line-number Precede each output line by its line number in the file, fol- - lowed by a colon and a space for matching lines or a hyphen - and a space for context lines. If the filename is also being - output, it precedes the line number. + lowed by a colon for matching lines or a hyphen for context + lines. If the filename is also being output, it precedes the + line number. This option is forced if --line-offsets is used. -o, --only-matching Show only the part of the line that matched a pattern. In this mode, no context is shown. That is, the -A, -B, and -C - options are ignored. + options are ignored. If there is more than one match in a + line, each of them is shown separately. If -o is combined + with -v (invert the sense of the match to find non-matching + lines), no output is generated, but the return code is set + appropriately. This option is mutually exclusive with --file- + offsets and --line-offsets. -q, --quiet Work quietly, that is, display nothing except error messages. - The exit status indicates whether or not any matches were + The exit status indicates whether or not any matches were found. -r, --recursive - If any given path is a directory, recursively scan the files - it contains, taking note of any --include and --exclude set- - tings. By default, a directory is read as a normal file; in - some operating systems this gives an immediate end-of-file. - This option is a shorthand for setting the -d option to + If any given path is a directory, recursively scan the files + it contains, taking note of any --include and --exclude set- + tings. By default, a directory is read as a normal file; in + some operating systems this gives an immediate end-of-file. + This option is a shorthand for setting the -d option to "recurse". -s, --no-messages - Suppress error messages about non-existent or unreadable - files. Such files are quietly skipped. However, the return + Suppress error messages about non-existent or unreadable + files. Such files are quietly skipped. However, the return code is still 2, even if matches were found in other files. -u, --utf-8 - Operate in UTF-8 mode. This option is available only if PCRE - has been compiled with UTF-8 support. Both patterns and sub- + Operate in UTF-8 mode. This option is available only if PCRE + has been compiled with UTF-8 support. Both patterns and sub- ject lines must be valid strings of UTF-8 characters. -V, --version - Write the version numbers of pcregrep and the PCRE library + Write the version numbers of pcregrep and the PCRE library that is being used to the standard error stream. -v, --invert-match - Invert the sense of the match, so that lines which do not + Invert the sense of the match, so that lines which do not match any of the patterns are the ones that are found. -w, --word-regex, --word-regexp @@ -306,61 +411,61 @@ lent to having \b at the start and end of the pattern. -x, --line-regex, --line-regexp - Force the patterns to be anchored (each must start matching - at the beginning of a line) and in addition, require them to - match entire lines. This is equivalent to having ^ and $ + Force the patterns to be anchored (each must start matching + at the beginning of a line) and in addition, require them to + match entire lines. This is equivalent to having ^ and $ characters at the start and end of each alternative branch in every pattern. ENVIRONMENT VARIABLES - The environment variables LC_ALL and LC_CTYPE are examined, in that - order, for a locale. The first one that is set is used. This can be - overridden by the --locale option. If no locale is set, the PCRE + The environment variables LC_ALL and LC_CTYPE are examined, in that + order, for a locale. The first one that is set is used. This can be + overridden by the --locale option. If no locale is set, the PCRE library's default (usually the "C" locale) is used. NEWLINES - The -N (--newline) option allows pcregrep to scan files with different - newline conventions from the default. However, the setting of this - option does not affect the way in which pcregrep writes information to - the standard error and output streams. It uses the string "\n" in C - printf() calls to indicate newlines, relying on the C I/O library to - convert this to an appropriate sequence if the output is sent to a + The -N (--newline) option allows pcregrep to scan files with different + newline conventions from the default. However, the setting of this + option does not affect the way in which pcregrep writes information to + the standard error and output streams. It uses the string "\n" in C + printf() calls to indicate newlines, relying on the C I/O library to + convert this to an appropriate sequence if the output is sent to a file. OPTIONS COMPATIBILITY The majority of short and long forms of pcregrep's options are the same - as in the GNU grep program. Any long option of the form --xxx-regexp - (GNU terminology) is also available as --xxx-regex (PCRE terminology). - However, the --locale, -M, --multiline, -u, and --utf-8 options are + as in the GNU grep program. Any long option of the form --xxx-regexp + (GNU terminology) is also available as --xxx-regex (PCRE terminology). + However, the --locale, -M, --multiline, -u, and --utf-8 options are specific to pcregrep. OPTIONS WITH DATA There are four different ways in which an option with data can be spec- - ified. If a short form option is used, the data may follow immedi- + ified. If a short form option is used, the data may follow immedi- ately, or in the next command line item. For example: -f/some/file -f /some/file - If a long form option is used, the data may appear in the same command + If a long form option is used, the data may appear in the same command line item, separated by an equals character, or (with one exception) it may appear in the next command line item. For example: --file=/some/file --file /some/file - Note, however, that if you want to supply a file name beginning with ~ - as data in a shell command, and have the shell expand ~ to a home + Note, however, that if you want to supply a file name beginning with ~ + as data in a shell command, and have the shell expand ~ to a home directory, you must separate the file name from the option, because the - shell does not treat ~ specially unless it is at the start of an item. + shell does not treat ~ specially unless it is at the start of an item. The exception to the above is the --colour (or --color) option, for which the data is optional. If this option does have data, it must be @@ -389,11 +494,19 @@ not affect the return code. +SEE ALSO + + pcrepattern(3), pcretest(1). + + AUTHOR Philip Hazel University Computing Service - Cambridge CB2 3QG, England. + Cambridge CB2 3QH, England. + + +REVISION -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + Last updated: 01 March 2009 + Copyright (c) 1997-2009 University of Cambridge. Modified: freeswitch/trunk/libs/pcre/doc/pcrematching.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrematching.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrematching.3 Mon Jun 8 18:51:30 2009 @@ -26,7 +26,7 @@ <something> <something else> <something further> .sp there are three possible answers. The standard algorithm finds only one of -them, whereas the DFA algorithm finds all three. +them, whereas the alternative algorithm finds all three. . .SH "REGULAR EXPRESSIONS AS TREES" .rs @@ -41,8 +41,8 @@ .SH "THE STANDARD MATCHING ALGORITHM" .rs .sp -In the terminology of Jeffrey Friedl's book \fIMastering Regular -Expressions\fP, the standard algorithm is an "NFA algorithm". It conducts a +In the terminology of Jeffrey Friedl's book "Mastering Regular +Expressions", the standard algorithm is an "NFA algorithm". It conducts a depth-first search of the pattern tree. That is, it proceeds along a single path through the tree, checking that the subject matches what is required. When there is a mismatch, the algorithm tries any alternatives at the current point, @@ -63,15 +63,16 @@ matched by portions of the pattern in parentheses. This provides support for capturing parentheses and back references. . -.SH "THE DFA MATCHING ALGORITHM" +.SH "THE ALTERNATIVE MATCHING ALGORITHM" .rs .sp -DFA stands for "deterministic finite automaton", but you do not need to -understand the origins of that name. This algorithm conducts a breadth-first -search of the tree. Starting from the first matching point in the subject, it -scans the subject string from left to right, once, character by character, and -as it does this, it remembers all the paths through the tree that represent -valid matches. +This algorithm conducts a breadth-first search of the tree. Starting from the +first matching point in the subject, it scans the subject string from left to +right, once, character by character, and as it does this, it remembers all the +paths through the tree that represent valid matches. In Friedl's terminology, +this is a kind of "DFA algorithm", though it is not implemented as a +traditional finite state machine (it keeps multiple states active +simultaneously). .P The scan continues until either the end of the subject is reached, or there are no more unterminated paths. At this point, terminated paths represent the @@ -92,11 +93,20 @@ matches that start at later positions. .P There are a number of features of PCRE regular expressions that are not -supported by the DFA matching algorithm. They are as follows: +supported by the alternative matching algorithm. They are as follows: .P 1. Because the algorithm finds all possible matches, the greedy or ungreedy nature of repetition quantifiers is not relevant. Greedy and ungreedy -quantifiers are treated in exactly the same way. +quantifiers are treated in exactly the same way. However, possessive +quantifiers can make a difference when what follows could also match what is +quantified, for example in a pattern like this: +.sp + ^a++\ew! +.sp +This pattern matches "aaab!" but not "aaa!", which would be matched by a +non-possessive quantifier. Similarly, if an atomic group is present, it is +matched as if it were a standalone pattern at the current point, and the +longest match is then "locked in" for the rest of the overall pattern. .P 2. When dealing with multiple paths through the tree simultaneously, it is not straightforward to keep track of captured substrings for the different matching @@ -107,21 +117,27 @@ not supported, and cause errors if encountered. .P 4. For the same reason, conditional expressions that use a backreference as the -condition are not supported. +condition or test for a specific group recursion are not supported. .P -5. Callouts are supported, but the value of the \fIcapture_top\fP field is +5. Because many paths through the tree may be active, the \eK escape sequence, +which resets the start of the match when encountered (but may be on some paths +and not on others), is not supported. It causes an error if encountered. +.P +6. Callouts are supported, but the value of the \fIcapture_top\fP field is always 1, and the value of the \fIcapture_last\fP field is always -1. .P -6. -The \eC escape sequence, which (in the standard algorithm) matches a single -byte, even in UTF-8 mode, is not supported because the DFA algorithm moves -through the subject string one character at a time, for all active paths +7. The \eC escape sequence, which (in the standard algorithm) matches a single +byte, even in UTF-8 mode, is not supported because the alternative algorithm +moves through the subject string one character at a time, for all active paths through the tree. +.P +8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not +supported. (*FAIL) is supported, and behaves like a failing negative assertion. . -.SH "ADVANTAGES OF THE DFA ALGORITHM" +.SH "ADVANTAGES OF THE ALTERNATIVE ALGORITHM" .rs .sp -Using the DFA matching algorithm provides the following advantages: +Using the alternative matching algorithm provides the following advantages: .P 1. All possible matches (at a single point in the subject) are automatically found, and in particular, the longest match is found. To find more than one @@ -130,17 +146,18 @@ .P 2. There is much better support for partial matching. The restrictions on the content of the pattern that apply when using the standard algorithm for partial -matching do not apply to the DFA algorithm. For non-anchored patterns, the -starting position of a partial match is available. +matching do not apply to the alternative algorithm. For non-anchored patterns, +the starting position of a partial match is available. .P -3. Because the DFA algorithm scans the subject string just once, and never -needs to backtrack, it is possible to pass very long subject strings to the -matching function in several pieces, checking for partial matching each time. +3. Because the alternative algorithm scans the subject string just once, and +never needs to backtrack, it is possible to pass very long subject strings to +the matching function in several pieces, checking for partial matching each +time. . -.SH "DISADVANTAGES OF THE DFA ALGORITHM" +.SH "DISADVANTAGES OF THE ALTERNATIVE ALGORITHM" .rs .sp -The DFA algorithm suffers from a number of disadvantages: +The alternative algorithm suffers from a number of disadvantages: .P 1. It is substantially slower than the standard algorithm. This is partly because it has to search for all possible matches, but is also because it is @@ -148,10 +165,24 @@ .P 2. Capturing parentheses and back references are not supported. .P -3. The "atomic group" feature of PCRE regular expressions is supported, but -does not provide the advantage that it does for the standard algorithm. -.P -.in 0 -Last updated: 06 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +3. Although atomic groups are supported, their use does not provide the +performance advantage that it does for the standard algorithm. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 19 April 2008 +Copyright (c) 1997-2008 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrepartial.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrepartial.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrepartial.3 Mon Jun 8 18:51:30 2009 @@ -71,6 +71,8 @@ .P If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, \fBpcre_exec()\fP returns the error code PCRE_ERROR_BADPARTIAL (-13). +You can use the PCRE_INFO_OKPARTIAL call to \fBpcre_fullinfo()\fP to find out +if a compiled pattern can be used for partial matching. . . .SH "EXAMPLE OF PARTIAL MATCHING USING PCRETEST" @@ -95,10 +97,11 @@ .sp The first data string is matched completely, so \fBpcretest\fP shows the matched substrings. The remaining four strings do not match the complete -pattern, but the first two are partial matches. The same test, using DFA -matching (by means of the \eD escape sequence), produces the following output: +pattern, but the first two are partial matches. The same test, using +\fBpcre_dfa_exec()\fP matching (by means of the \eD escape sequence), produces +the following output: .sp - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ data> 25jun04\eP\eD 0: 25jun04 data> 23dec3\eP\eD @@ -119,13 +122,13 @@ .sp When a partial match has been found using \fBpcre_dfa_exec()\fP, it is possible to continue the match by providing additional subject data and calling -\fBpcre_dfa_exec()\fP again with the PCRE_DFA_RESTART option and the same -working space (where details of the previous partial match are stored). Here is -an example using \fBpcretest\fP, where the \eR escape sequence sets the -PCRE_DFA_RESTART option and the \eD escape sequence requests the use of -\fBpcre_dfa_exec()\fP: +\fBpcre_dfa_exec()\fP again with the same compiled regular expression, this +time setting the PCRE_DFA_RESTART option. You must also pass the same working +space as before, because this is where details of the previous partial match +are stored. Here is an example using \fBpcretest\fP, using the \eR escape +sequence to set the PCRE_DFA_RESTART option (\eP and \eD are as above): .sp - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ data> 23ja\eP\eD Partial match: 23ja data> n05\eR\eD @@ -137,9 +140,10 @@ not retain the previously partially-matched string. It is up to the calling program to do that if it needs to. .P -This facility can be used to pass very long subject strings to -\fBpcre_dfa_exec()\fP. However, some care is needed for certain types of -pattern. +You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial matching +over multiple segments. This facility can be used to pass very long subject +strings to \fBpcre_dfa_exec()\fP. However, some care is needed for certain +types of pattern. .P 1. If the pattern contains tests for the beginning or end of a line, you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropriate, when the @@ -147,7 +151,7 @@ .P 2. If the pattern contains backward assertions (including \eb or \eB), you need to arrange for some overlap in the subject strings to allow for this. For -example, you could pass the subject in chunks that were 500 bytes long, but in +example, you could pass the subject in chunks that are 500 bytes long, but in a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 bytes at the start of the buffer. .P @@ -155,7 +159,7 @@ always produce exactly the same result as matching over one single long string. The difference arises when there are multiple matching possibilities, because a partial match result is given only when there are no completed matches in a -call to fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has +call to \fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has been found, continuation to a new subject segment is no longer possible. Consider this \fBpcretest\fP example: .sp @@ -196,8 +200,20 @@ where no string can be a partial match for both alternatives. . . -.P -.in 0 -Last updated: 16 January 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 04 June 2007 +Copyright (c) 1997-2007 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrepattern.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrepattern.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrepattern.3 Mon Jun 8 18:51:30 2009 @@ -4,18 +4,34 @@ .SH "PCRE REGULAR EXPRESSION DETAILS" .rs .sp -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of books, some of which have copious examples. -Jeffrey Friedl's "Mastering Regular Expressions", published by O'Reilly, covers -regular expressions in great detail. This description of PCRE's regular -expressions is intended as reference material. +The syntax and semantics of the regular expressions that are supported by PCRE +are described in detail below. There is a quick-reference syntax summary in the +.\" HREF +\fBpcresyntax\fP +.\" +page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE +also supports some alternative regular expression syntax (which does not +conflict with the Perl syntax) in order to provide some compatibility with +regular expressions in Python, .NET, and Oniguruma. +.P +Perl's regular expressions are described in its own documentation, and +regular expressions in general are covered in a number of books, some of which +have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", +published by O'Reilly, covers regular expressions in great detail. This +description of PCRE's regular expressions is intended as reference material. .P The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 character strings. To use this, you must build PCRE to include UTF-8 support, and then call \fBpcre_compile()\fP with -the PCRE_UTF8 option. How this affects pattern matching is mentioned in several -places below. There is also a summary of UTF-8 features in the +the PCRE_UTF8 option. There is also a special sequence that can be given at the +start of a pattern: +.sp + (*UTF8) +.sp +Starting a pattern with this sequence is equivalent to setting the PCRE_UTF8 +option. This feature is not Perl-compatible. How setting UTF-8 mode affects +pattern matching is mentioned in several places below. There is also a summary +of UTF-8 features in the .\" HTML <a href="pcre.html#utf8support"> .\" </a> section on UTF-8 support @@ -30,13 +46,68 @@ PCRE when its main matching function, \fBpcre_exec()\fP, is used. From release 6.0, PCRE offers a second matching function, \fBpcre_dfa_exec()\fP, which matches using a different algorithm that is not -Perl-compatible. The advantages and disadvantages of the alternative function, -and how it differs from the normal function, are discussed in the +Perl-compatible. Some of the features discussed below are not available when +\fBpcre_dfa_exec()\fP is used. The advantages and disadvantages of the +alternative function, and how it differs from the normal function, are +discussed in the .\" HREF \fBpcrematching\fP .\" page. +. +. +.SH "NEWLINE CONVENTIONS" +.rs +.sp +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The +.\" HREF +\fBpcreapi\fP +.\" +page has +.\" HTML <a href="pcreapi.html#newlines"> +.\" </a> +further discussion +.\" +about newlines, and shows how to set the newline convention in the +\fIoptions\fP arguments for the compiling and matching functions. .P +It is also possible to specify a newline convention by starting a pattern +string with one of the following five sequences: +.sp + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences +.sp +These override the default and the options given to \fBpcre_compile()\fP. For +example, on a Unix system where LF is the default newline sequence, the pattern +.sp + (*CR)a.b +.sp +changes the convention to CR. That pattern matches "a\enb" because LF is no +longer a newline. Note that these special settings, which are not +Perl-compatible, are recognized only at the very start of a pattern, and that +they must be in upper case. If more than one of them is present, the last one +is used. +.P +The newline convention does not affect what the \eR escape sequence matches. By +default, this is any Unicode newline sequence, for Perl compatibility. However, +this can be changed; see the description of \eR in the section entitled +.\" HTML <a href="#newlineseq"> +.\" </a> +"Newline sequences" +.\" +below. A change of \eR setting can be combined with a change of newline +convention. +. +. +.SH "CHARACTERS AND METACHARACTERS" +.rs +.sp A regular expression is a pattern that is matched against a subject string from left to right. Most characters stand for themselves in a pattern, and match the corresponding characters in the subject. As a trivial example, the pattern @@ -60,8 +131,8 @@ .P There are two different sets of metacharacters: those that are recognized anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the metacharacters are -as follows: +recognized within square brackets. Outside square brackets, the metacharacters +are as follows: .sp \e general escape character with several uses ^ assert start of string (or line, in multiline mode) @@ -92,6 +163,7 @@ .sp The following sections describe the use of each of the metacharacters. . +. .SH BACKSLASH .rs .sp @@ -142,7 +214,7 @@ \ecx "control-x", where x is any character \ee escape (hex 1B) \ef formfeed (hex 0C) - \en newline (hex 0A) + \en linefeed (hex 0A) \er carriage return (hex 0D) \et tab (hex 09) \eddd character with octal code ddd, or backreference @@ -157,11 +229,14 @@ After \ex, from zero to two hexadecimal digits are read (letters can be in upper or lower case). Any number of hexadecimal digits may appear between \ex{ and }, but the value of the character code must be less than 256 in non-UTF-8 -mode, and less than 2**31 in UTF-8 mode (that is, the maximum hexadecimal value -is 7FFFFFFF). If characters other than hexadecimal digits appear between \ex{ -and }, or if there is no terminating }, this form of escape is not recognized. -Instead, the initial \ex will be interpreted as a basic hexadecimal escape, -with no following digits, giving a character whose value is zero. +mode, and less than 2**31 in UTF-8 mode. That is, the maximum value in +hexadecimal is 7FFFFFFF. Note that this is bigger than the largest Unicode code +point, which is 10FFFF. +.P +If characters other than hexadecimal digits appear between \ex{ and }, or if +there is no terminating }, this form of escape is not recognized. Instead, the +initial \ex will be interpreted as a basic hexadecimal escape, with no +following digits, giving a character whose value is zero. .P Characters whose value is less than 256 can be defined by either of the two syntaxes for \ex. There is no difference in the way they are handled. For @@ -190,7 +265,7 @@ .P Inside a character class, or if the decimal number is greater than 9 and there have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, ane uses them to generate a data character. Any +digits following the backslash, and uses them to generate a data character. Any subsequent digits stand for themselves. In non-UTF-8 mode, the value of a character specified in octal must be less than \e400. In UTF-8 mode, values up to \e777 are permitted. For example: @@ -221,24 +296,60 @@ All the sequences that define a single character value can be used both inside and outside character classes. In addition, inside a character class, the sequence \eb is interpreted as the backspace character (hex 08), and the -sequence \eX is interpreted as the character "X". Outside a character class, -these sequences have different meanings +sequences \eR and \eX are interpreted as the characters "R" and "X", +respectively. Outside a character class, these sequences have different +meanings .\" HTML <a href="#uniextseq"> .\" </a> (see below). .\" . . +.SS "Absolute and relative back references" +.rs +.sp +The sequence \eg followed by an unsigned or a negative number, optionally +enclosed in braces, is an absolute or relative back reference. A named back +reference can be coded as \eg{name}. Back references are discussed +.\" HTML <a href="#backreferences"> +.\" </a> +later, +.\" +following the discussion of +.\" HTML <a href="#subpattern"> +.\" </a> +parenthesized subpatterns. +.\" +. +. +.SS "Absolute and relative subroutine calls" +.rs +.sp +For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a "subroutine". Details are discussed +.\" HTML <a href="#onigurumasubroutines"> +.\" </a> +later. +.\" +Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP +synonymous. The former is a back reference; the latter is a subroutine call. +. +. .SS "Generic character types" .rs .sp -The third use of backslash is for specifying generic character types. The +Another use of backslash is for specifying generic character types. The following are always recognized: .sp \ed any decimal digit \eD any character that is not a decimal digit + \eh any horizontal whitespace character + \eH any character that is not a horizontal whitespace character \es any whitespace character \eS any character that is not a whitespace character + \ev any vertical whitespace character + \eV any character that is not a vertical whitespace character \ew any "word" character \eW any "non-word" character .sp @@ -252,9 +363,50 @@ .P For compatibility with Perl, \es does not match the VT character (code 11). This makes it different from the the POSIX "space" class. The \es characters -are HT (9), LF (10), FF (12), CR (13), and space (32). (If "use locale;" is +are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is included in a Perl script, \es may match the VT character. In PCRE, it never -does.) +does. +.P +In UTF-8 mode, characters with values greater than 128 never match \ed, \es, or +\ew, and always match \eD, \eS, and \eW. This is true even when Unicode +character property support is available. These sequences retain their original +meanings from before UTF-8 support was available, mainly for efficiency +reasons. Note that this also affects \eb, because it is defined in terms of \ew +and \eW. +.P +The sequences \eh, \eH, \ev, and \eV are Perl 5.10 features. In contrast to the +other sequences, these do match certain high-valued codepoints in UTF-8 mode. +The horizontal space characters are: +.sp + U+0009 Horizontal tab + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space +.sp +The vertical space characters are: +.sp + U+000A Linefeed + U+000B Vertical tab + U+000C Formfeed + U+000D Carriage return + U+0085 Next line + U+2028 Line separator + U+2029 Paragraph separator .P A "word" character is an underscore or any character less than 256 that is a letter or digit. The definition of letters and digits is controlled by PCRE's @@ -268,13 +420,59 @@ .\" HREF \fBpcreapi\fP .\" -page). For example, in the "fr_FR" (French) locale, some character codes -greater than 128 are used for accented letters, and these are matched by \ew. -.P -In UTF-8 mode, characters with values greater than 128 never match \ed, \es, or -\ew, and always match \eD, \eS, and \eW. This is true even when Unicode -character property support is available. The use of locales with Unicode is -discouraged. +page). For example, in a French locale such as "fr_FR" in Unix-like systems, +or "french" in Windows, some character codes greater than 128 are used for +accented letters, and these are matched by \ew. The use of locales with Unicode +is discouraged. +. +. +.\" HTML <a name="newlineseq"></a> +.SS "Newline sequences" +.rs +.sp +Outside a character class, by default, the escape sequence \eR matches any +Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \eR is +equivalent to the following: +.sp + (?>\er\en|\en|\ex0b|\ef|\er|\ex85) +.sp +This is an example of an "atomic group", details of which are given +.\" HTML <a href="#atomicgroup"> +.\" </a> +below. +.\" +This particular group matches either the two-character sequence CR followed by +LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, +U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next +line, U+0085). The two-character sequence is treated as a single unit that +cannot be split. +.P +In UTF-8 mode, two additional characters whose codepoints are greater than 255 +are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). +Unicode character property support is not needed for these characters to be +recognized. +.P +It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. (BSR is an abbrevation +for "backslash R".) This can be made the default when PCRE is built; if this is +the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. +It is also possible to specify these settings by starting a pattern string with +one of the following sequences: +.sp + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +.sp +These override the default and the options given to \fBpcre_compile()\fP, but +they can be overridden by options given to \fBpcre_exec()\fP. Note that these +special settings, which are not Perl-compatible, are recognized only at the +very start of a pattern, and that they must be in upper case. If more than one +of them is present, the last one is used. They can be combined with a change of +newline convention, for example, a pattern can start with: +.sp + (*ANY)(*BSR_ANYCRLF) +.sp +Inside a character class, \eR matches the letter "R". . . .\" HTML <a name="uniextseq"></a> @@ -282,8 +480,10 @@ .rs .sp When PCRE is built with Unicode character property support, three additional -escape sequences to match character properties are available when UTF-8 mode -is selected. They are: +escape sequences that match characters with specific properties are available. +When not in UTF-8 mode, these sequences are of course limited to testing +characters whose codepoints are less than 256, but they do work in this mode. +The extra escape sequences are: .sp \ep{\fIxx\fP} a character with the \fIxx\fP property \eP{\fIxx\fP} a character without the \fIxx\fP property @@ -307,6 +507,7 @@ .P Arabic, Armenian, +Balinese, Bengali, Bopomofo, Braille, @@ -316,6 +517,7 @@ Cherokee, Common, Coptic, +Cuneiform, Cypriot, Cyrillic, Deseret, @@ -345,11 +547,14 @@ Mongolian, Myanmar, New_Tai_Lue, +Nko, Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, +Phags_Pa, +Phoenician, Runic, Shavian, Sinhala, @@ -430,6 +635,15 @@ the Lu, Ll, or Lt property, in other words, a letter that is not classified as a modifier or "other". .P +The Cs (Surrogate) property applies only to characters in the range U+D800 to +U+DFFF. Such characters are not valid in UTF-8 strings (see RFC 3629) and so +cannot be tested by PCRE, unless UTF-8 validity checking has been turned off +(see the discussion of PCRE_NO_UTF8_CHECK in the +.\" HREF +\fBpcreapi\fP +.\" +page). +.P The long synonyms for these properties that Perl supports (such as \ep{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". @@ -454,7 +668,8 @@ (see below). .\" Characters with the "mark" property are typically accents that affect the -preceding character. +preceding character. None of them have codepoints less than 256, so in +non-UTF-8 mode \eX matches any one character. .P Matching characters by Unicode property is not fast, because PCRE has to search a structure that contains data for over fifteen thousand characters. That is @@ -462,11 +677,41 @@ properties in PCRE. . . +.\" HTML <a name="resetmatchstart"></a> +.SS "Resetting the match start" +.rs +.sp +The escape sequence \eK, which is a Perl 5.10 feature, causes any previously +matched characters not to be included in the final matched sequence. For +example, the pattern: +.sp + foo\eKbar +.sp +matches "foobar", but reports that it has matched "bar". This feature is +similar to a lookbehind assertion +.\" HTML <a href="#lookbehind"> +.\" </a> +(described below). +.\" +However, in this case, the part of the subject before the real match does not +have to be of fixed length, as lookbehind assertions do. The use of \eK does +not interfere with the setting of +.\" HTML <a href="#subpattern"> +.\" </a> +captured substrings. +.\" +For example, when the pattern +.sp + (foo)\eKbar +.sp +matches "foobar", the first substring is still set to "foo". +. +. .\" HTML <a name="smallassertions"></a> .SS "Simple assertions" .rs .sp -The fourth use of backslash is for certain simple assertions. An assertion +The final use of backslash is for certain simple assertions. An assertion specifies a condition that has to be met at a particular point in a match, without consuming any characters from the subject string. The use of subpatterns for more complicated assertions is described @@ -478,10 +723,11 @@ .sp \eb matches at a word boundary \eB matches when not at a word boundary - \eA matches at start of subject - \eZ matches at end of subject or before newline at end - \ez matches at end of subject - \eG matches at first matching position in subject + \eA matches at the start of the subject + \eZ matches at the end of the subject + also matches before a newline at the end of the subject + \ez matches only at the end of the subject + \eG matches at the first matching position in the subject .sp These assertions may not appear in character classes (but note that \eb has a different meaning, namely the backspace character, inside a character class). @@ -578,15 +824,19 @@ .sp Outside a character class, a dot in the pattern matches any one character in the subject string except (by default) a character that signifies the end of a -line. In UTF-8 mode, the matched character may be more than one byte long. When -a line ending is defined as a single character (CR or LF), dot never matches -that character; when the two-character sequence CRLF is used, dot does not -match CR if it is immediately followed by LF, but otherwise it matches all -characters (including isolated CRs and LFs). +line. In UTF-8 mode, the matched character may be more than one byte long. +.P +When a line ending is defined as a single character, dot never matches that +character; when the two-character sequence CRLF is used, dot does not match CR +if it is immediately followed by LF, but otherwise it matches all characters +(including isolated CRs and LFs). When any Unicode line endings are being +recognized, dot does not match CR or LF or any of the other line ending +characters. .P The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL -option is set, a dot matches any one character, without exception. If newline -is defined as the two-character sequence CRLF, it takes two dots to match it. +option is set, a dot matches any one character, without exception. If the +two-character sequence CRLF is present in the subject string, it takes two dots +to match it. .P The handling of dot is entirely independent of the handling of circumflex and dollar, the only relationship being that they both involve newlines. Dot has no @@ -597,11 +847,11 @@ .rs .sp Outside a character class, the escape sequence \eC matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches CR and LF. The -feature is provided in Perl in order to match individual bytes in UTF-8 mode. -Because it breaks up UTF-8 characters into individual bytes, what remains in -the string may be a malformed UTF-8 string. For this reason, the \eC escape -sequence is best avoided. +in and out of UTF-8 mode. Unlike a dot, it always matches any line-ending +characters. The feature is provided in Perl in order to match individual bytes +in UTF-8 mode. Because it breaks up UTF-8 characters into individual bytes, +what remains in the string may be a malformed UTF-8 string. For this reason, +the \eC escape sequence is best avoided. .P PCRE does not allow \eC to appear in lookbehind assertions .\" HTML <a href="#lookbehind"> @@ -652,10 +902,10 @@ ensure that PCRE is compiled with Unicode property support as well as with UTF-8 support. .P -Characters that might indicate line breaks (CR and LF) are never treated in any -special way when matching character classes, whatever line-ending sequence is -in use, and whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is -used. A class such as [^a] always matches one of these characters. +Characters that might indicate line breaks are never treated in any special way +when matching character classes, whatever line-ending sequence is in use, and +whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class +such as [^a] always matches one of these characters. .P The minus (hyphen) character can be used to specify a range of characters in a character class. For example, [d-m] matches any letter between d and m, @@ -679,7 +929,7 @@ If a range that includes letters is used when caseless matching is set, it matches the letters in either case. For example, [W-c] is equivalent to [][\e\e^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character -tables for the "fr_FR" locale are in use, [\exc8-\excb] matches accented E +tables for a French locale are in use, [\exc8-\excb] matches accented E characters in both cases. In UTF-8 mode, PCRE supports the concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. @@ -769,8 +1019,9 @@ .rs .sp The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options can be changed from within the pattern by a sequence of -Perl option letters enclosed between "(?" and ")". The option letters are +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are .sp i for PCRE_CASELESS m for PCRE_MULTILINE @@ -784,14 +1035,18 @@ permitted. If a letter appears both before and after the hyphen, the option is unset. .P -When an option change occurs at top level (that is, not inside subpattern -parentheses), the change applies to the remainder of the pattern that follows. -If the change is placed right at the start of a pattern, PCRE extracts it into -the global options (and it will therefore show up in data extracted by the -\fBpcre_fullinfo()\fP function). +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +.P +When one of these option changes occurs at top level (that is, not inside +subpattern parentheses), the change applies to the remainder of the pattern +that follows. If the change is placed right at the start of a pattern, PCRE +extracts it into the global options (and it will therefore show up in data +extracted by the \fBpcre_fullinfo()\fP function). .P -An option change within a subpattern affects only that part of the current -pattern that follows it, so +An option change within a subpattern (see below for a description of +subpatterns) affects only that part of the current pattern that follows it, so .sp (a(?i)b)c .sp @@ -807,9 +1062,17 @@ option settings happen at compile time. There would be some very weird behaviour otherwise. .P -The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be -changed in the same way as the Perl-compatible options by using the characters -J, U and X respectively. +\fBNote:\fP There are other PCRE-specific options that can be set by the +application when the compile or match functions are called. In some cases the +pattern can contain special leading sequences such as (*CRLF) to override what +the application has set or what has been defaulted. Details are given in the +section entitled +.\" HTML <a href="#newlineseq"> +.\" </a> +"Newline sequences" +.\" +above. There is also the (*UTF8) leading sequence that can be used to set UTF-8 +mode; this is equivalent to setting the PCRE_UTF8 option. . . .\" HTML <a name="subpattern"></a> @@ -824,7 +1087,7 @@ cat(aract|erpillar|) .sp matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. +parentheses, it would match "cataract", "erpillar" or an empty string. .sp 2. It sets up the subpattern as a capturing subpattern. This means that, when the whole pattern matches, that portion of the subject string that matched the @@ -849,8 +1112,7 @@ the ((?:red|white) (king|queen)) .sp the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535, and the maximum depth -of nesting of all subpatterns, both capturing and non-capturing, is 200. +2. The maximum number of capturing subpatterns is 65535. .P As a convenient shorthand, if any option settings are required at the start of a non-capturing subpattern, the option letters may appear between the "?" and @@ -865,14 +1127,51 @@ the above patterns match "SUNDAY" as well as "Saturday". . . +.SH "DUPLICATE SUBPATTERN NUMBERS" +.rs +.sp +Perl 5.10 introduced a feature whereby each alternative in a subpattern uses +the same numbers for its capturing parentheses. Such a subpattern starts with +(?| and is itself a non-capturing subpattern. For example, consider this +pattern: +.sp + (?|(Sat)ur|(Sun))day +.sp +Because the two alternatives are inside a (?| group, both sets of capturing +parentheses are numbered one. Thus, when the pattern matches, you can look +at captured substring number one, whichever alternative matched. This construct +is useful when you want to capture part, but not all, of one of a number of +alternatives. Inside a (?| group, parentheses are numbered as usual, but the +number is reset at the start of each branch. The numbers of any capturing +buffers that follow the subpattern start after the highest number used in any +branch. The following example is taken from the Perl documentation. +The numbers underneath show in which buffer the captured content will be +stored. +.sp + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 +.sp +A backreference or a recursive call to a numbered subpattern always refers to +the first one in the pattern with the given number. +.P +An alternative approach to using this "branch reset" feature is to use +duplicate named subpatterns, as described in the next section. +. +. .SH "NAMED SUBPATTERNS" .rs .sp Identifying capturing parentheses by number is simple, but it can be very hard to keep track of the numbers in complicated regular expressions. Furthermore, if an expression is modified, the numbers may change. To help with this -difficulty, PCRE supports the naming of subpatterns, something that Perl does -not provide. The Python syntax (?P<name>...) is used. References to capturing +difficulty, PCRE supports the naming of subpatterns. This feature was not +added to Perl until release 5.10. Python had the feature earlier, and PCRE +introduced it at release 4.0, using the Python syntax. PCRE now supports both +the Perl and the Python syntax. +.P +In PCRE, a subpattern can be named in one of three ways: (?<name>...) or +(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing parentheses from other parts of the pattern, such as .\" HTML <a href="#backreferences"> .\" </a> @@ -890,10 +1189,10 @@ can be made by name as well as by number. .P Names consist of up to 32 alphanumeric characters and underscores. Named -capturing parentheses are still allocated numbers as well as names. The PCRE -API provides function calls for extracting the name-to-number translation table -from a compiled pattern. There is also a convenience function for extracting a -captured substring by name. +capturing parentheses are still allocated numbers as well as names, exactly as +if the names were not present. The PCRE API provides function calls for +extracting the name-to-number translation table from a compiled pattern. There +is also a convenience function for extracting a captured substring by name. .P By default, a name must be unique within a pattern, but it is possible to relax this constraint by setting the PCRE_DUPNAMES option at compile time. This can @@ -902,15 +1201,18 @@ abbreviation or as the full name, and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: .sp - (?P<DN>Mon|Fri|Sun)(?:day)?| - (?P<DN>Tue)(?:sday)?| - (?P<DN>Wed)(?:nesday)?| - (?P<DN>Thu)(?:rsday)?| - (?P<DN>Sat)(?:urday)? + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? .sp There are five capturing substrings, but only one is ever set after a match. +(An alternative way of solving this problem is to use a "branch reset" +subpattern, as described in the previous section.) +.P The convenience function for extracting the data by name returns the substring -for the first, and in this example, the only, subpattern of that name that +for the first (and in this example, the only) subpattern of that name that matched. This saves searching to find which numbered subpattern it was. If you make a reference to a non-unique named subpattern from elsewhere in the pattern, the one that corresponds to the lowest number is used. For further @@ -919,6 +1221,10 @@ \fBpcreapi\fP .\" documentation. +.P +\fBWarning:\fP You cannot use different names to distinguish between two +subpatterns with the same number (see the previous section) because PCRE uses +only the numbers when matching. . . .SH REPETITION @@ -928,9 +1234,10 @@ items: .sp a literal data character - the . metacharacter + the dot metacharacter the \eC escape sequence the \eX escape sequence (in UTF-8 mode with Unicode properties) + the \eR escape sequence an escape such as \ed that matches a single character a character class a back reference (see next section) @@ -966,10 +1273,17 @@ which may be several bytes long (and they may be of different lengths). .P The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. +previous item and the quantifier were not present. This may be useful for +subpatterns that are referenced as +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +subroutines +.\" +from elsewhere in the pattern. Items other than subpatterns that have a {0} +quantifier are omitted from the compiled pattern. .P -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: +For convenience, the three most common quantifiers have single-character +abbreviations: .sp * is equivalent to {0,} + is equivalent to {1,} @@ -1017,7 +1331,7 @@ which matches one digit by preference, but can match two if that is the only way the rest of the pattern matches. .P -If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +If the PCRE_UNGREEDY option is set (an option that is not available in Perl), the quantifiers are not greedy by default, but individual ones can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. @@ -1027,7 +1341,7 @@ compiled pattern, in proportion to the size of the minimum or maximum. .P If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is implicitly anchored, because whatever follows will be tried against every character position in the subject string, so there is no point in retrying the overall match at any position after the first. PCRE normally treats such a @@ -1039,8 +1353,8 @@ .P However, there is one situation where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail, and a later one -succeed. Consider, for example: +elsewhere in the pattern, a match at the start may fail where a later one +succeeds. Consider, for example: .sp (.*)abc\e1 .sp @@ -1066,12 +1380,12 @@ .SH "ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS" .rs .sp -With both maximizing and minimizing repetition, failure of what follows -normally causes the repeated item to be re-evaluated to see if a different -number of repeats allows the rest of the pattern to match. Sometimes it is -useful to prevent this, either to change the nature of the match, or to cause -it fail earlier than it otherwise might, when the author of the pattern knows -there is no point in carrying on. +With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") +repetition, failure of what follows normally causes the repeated item to be +re-evaluated to see if a different number of repeats allows the rest of the +pattern to match. Sometimes it is useful to prevent this, either to change the +nature of the match, or to cause it fail earlier than it otherwise might, when +the author of the pattern knows there is no point in carrying on. .P Consider, for example, the pattern \ed+foo when applied to the subject line .sp @@ -1083,7 +1397,7 @@ (a term taken from Jeffrey Friedl's book) provides the means for specifying that once a subpattern has matched, it is not to be re-evaluated in this way. .P -If we use atomic grouping for the previous example, the matcher would give up +If we use atomic grouping for the previous example, the matcher gives up immediately on failing to match "foo" the first time. The notation is a kind of special parenthesis, starting with (?> as in this example: .sp @@ -1113,15 +1427,26 @@ .sp \ed++foo .sp +Note that a possessive quantifier can be used with an entire group, for +example: +.sp + (abc|xyz){2,3}+ +.sp Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning or processing of a -possessive quantifier and the equivalent atomic group. -.P -The possessive quantifier syntax is an extension to the Perl syntax. Jeffrey -Friedl originated the idea (and the name) in the first edition of his book. -Mike McCloskey liked it, so implemented it when he built Sun's Java package, -and PCRE copied it from there. +atomic group. However, there is no difference in the meaning of a possessive +quantifier and the equivalent atomic group, though there may be a performance +difference; possessive quantifiers should be slightly faster. +.P +The possessive quantifier syntax is an extension to the Perl 5.8 syntax. +Jeffrey Friedl originated the idea (and the name) in the first edition of his +book. Mike McCloskey liked it, so implemented it when he built Sun's Java +package, and PCRE copied it from there. It ultimately found its way into Perl +at release 5.10. +.P +PCRE has an optimization that automatically "possessifies" certain simple +pattern constructs. For example, the sequence A+B is treated as A++B because +there is no point in backtracking into a sequence of A's when B must follow. .P When a pattern contains an unlimited repeat inside a subpattern that can itself be repeated an unlimited number of times, the use of an atomic group is the @@ -1167,15 +1492,39 @@ when a repetition is involved and the subpattern to the right has participated in an earlier iteration. .P -It is not possible to have a numerical "forward back reference" to subpattern -whose number is 10 or more. However, a back reference to any subpattern is -possible using named parentheses (see below). See also the subsection entitled +It is not possible to have a numerical "forward back reference" to a subpattern +whose number is 10 or more using this syntax because a sequence such as \e50 is +interpreted as a character defined in octal. See the subsection entitled "Non-printing characters" .\" HTML <a href="#digitsafterbackslash"> .\" </a> above .\" -for further details of the handling of digits following a backslash. +for further details of the handling of digits following a backslash. There is +no such problem when named parentheses are used. A back reference to any +subpattern is possible using named parentheses (see below). +.P +Another way of avoiding the ambiguity inherent in the use of digits following a +backslash is to use the \eg escape sequence, which is a feature introduced in +Perl 5.10. This escape must be followed by an unsigned number or a negative +number, optionally enclosed in braces. These examples are all identical: +.sp + (ring), \e1 + (ring), \eg1 + (ring), \eg{1} +.sp +An unsigned number specifies an absolute reference without the ambiguity that +is present in the older syntax. It is also useful when literal digits follow +the reference. A negative number is a relative reference. Consider this +example: +.sp + (abc(def)ghi)\eg{-1} +.sp +The sequence \eg{-1} is a reference to the most recently started capturing +subpattern before \eg, that is, is it equivalent to \e2. Similarly, \eg{-2} +would be equivalent to \e1. The use of relative references can be helpful in +long patterns, and also in patterns that are created by joining together +fragments that contain references within themselves. .P A back reference matches whatever actually matched the capturing subpattern in the current subject string, rather than anything matching the subpattern @@ -1197,10 +1546,17 @@ matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capturing subpattern is matched caselessly. .P -Back references to named subpatterns use the Python syntax (?P=name). We could -rewrite the above example as follows: +There are several different ways of writing back references to named +subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek<name> or +\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified +back reference syntax, in which \eg can be used for both numeric and named +references, is also supported. We could rewrite the above example in any of +the following ways: .sp + (?<p1>(?i)rah)\es+\ek<p1> + (?'p1'(?i)rah)\es+\ek{p1} (?P<p1>(?i)rah)\es+(?P=p1) + (?<p1>(?i)rah)\es+\eg{p1} .sp A subpattern that is referenced by name may appear in the pattern before or after the reference. @@ -1323,19 +1679,27 @@ .sp (?<=abc|abde) .sp +In some cases, the Perl 5.10 escape sequence \eK +.\" HTML <a href="#resetmatchstart"> +.\" </a> +(see above) +.\" +can be used instead of a lookbehind assertion; this is not restricted to a +fixed-length. +.P The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed width and then try to +temporarily move the current position back by the fixed length and then try to match. If there are insufficient characters before the current position, the -match is deemed to fail. +assertion fails. .P PCRE does not allow the \eC escape (which matches a single byte in UTF-8 mode) to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. The \eX escape, which can match different numbers -of bytes, is also not permitted. +the length of the lookbehind. The \eX and \eR escapes, which can match +different numbers of bytes, are also not permitted. .P -Atomic groups can be used in conjunction with lookbehind assertions to specify -efficient matching at the end of the subject string. Consider a simple pattern -such as +Possessive quantifiers can be used in conjunction with lookbehind assertions to +specify efficient matching at the end of the subject string. Consider a simple +pattern such as .sp abcd$ .sp @@ -1351,13 +1715,9 @@ covers the entire string, from right to left, so we are no better off. However, if the pattern is written as .sp - ^(?>.*)(?<=abcd) -.sp -or, equivalently, using the possessive quantifier syntax, -.sp ^.*+(?<=abcd) .sp -there can be no backtracking for the .* item; it can match only the entire +there can be no backtracking for the .*+ item; it can match only the entire string. The subsequent lookbehind assertion does a single test on the last four characters. If it fails, the match fails immediately. For long strings, this approach makes a significant difference to the processing time. @@ -1413,15 +1773,19 @@ no-pattern (if present) is used. If there are more than two alternatives in the subpattern, a compile-time error occurs. .P -There are three kinds of condition. If the text between the parentheses -consists of a sequence of digits, or a sequence of alphanumeric characters and -underscores, the condition is satisfied if the capturing subpattern of that -number or name has previously matched. There is a possible ambiguity here, -because subpattern names may consist entirely of digits. PCRE looks first for a -named subpattern; if it cannot find one and the text consists entirely of -digits, it looks for a subpattern of that number, which must be greater than -zero. Using subpattern names that consist entirely of digits is not -recommended. +There are four kinds of condition: references to subpatterns, references to +recursion, a pseudo-condition called DEFINE, and assertions. +. +.SS "Checking for a used subpattern by number" +.rs +.sp +If the text between the parentheses consists of a sequence of digits, the +condition is true if the capturing subpattern of that number has previously +matched. An alternative notation is to precede the digits with a plus or minus +sign. In this case, the subpattern number is relative rather than absolute. +The most recently opened parentheses can be referenced by (?(-1), the next most +recent by (?(-2), and so on. In looping constructs it can also make sense to +refer to subsequent groups with constructs such as (?(+2). .P Consider the following pattern, which contains non-significant white space to make it more readable (assume the PCRE_EXTENDED option) and to divide it into @@ -1437,17 +1801,76 @@ the condition is true, and so the yes-pattern is executed and a closing parenthesis is required. Otherwise, since no-pattern is not present, the subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. Rewriting it to use a -named subpattern gives this: +non-parentheses, optionally enclosed in parentheses. +.P +If you were embedding this pattern in a larger one, you could use a relative +reference: +.sp + ...other stuff... ( \e( )? [^()]+ (?(-1) \e) ) ... +.sp +This makes the fragment independent of the parentheses in the larger pattern. +. +.SS "Checking for a used subpattern by name" +.rs +.sp +Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used +subpattern by name. For compatibility with earlier versions of PCRE, which had +this facility before Perl, the syntax (?(name)...) is also recognized. However, +there is a possible ambiguity with this syntax, because subpattern names may +consist entirely of digits. PCRE looks first for a named subpattern; if it +cannot find one and the name consists entirely of digits, PCRE looks for a +subpattern of that number, which must be greater than zero. Using subpattern +names that consist entirely of digits is not recommended. +.P +Rewriting the above example to use a named subpattern gives this: .sp - (?P<OPEN> \e( )? [^()]+ (?(OPEN) \e) ) + (?<OPEN> \e( )? [^()]+ (?(<OPEN>) \e) ) +.sp +. +.SS "Checking for pattern recursion" +.rs .sp If the condition is the string (R), and there is no subpattern with the name R, -the condition is satisfied if a recursive call to the pattern or subpattern has -been made. At "top level", the condition is false. This is a PCRE extension. -Recursive patterns are described in the next section. +the condition is true if a recursive call to the whole pattern or any +subpattern has been made. If digits or a name preceded by ampersand follow the +letter R, for example: +.sp + (?(R3)...) or (?(R&name)...) +.sp +the condition is true if the most recent recursion is into the subpattern whose +number or name is given. This condition does not check the entire recursion +stack. +.P +At "top level", all these recursion test conditions are false. Recursive +patterns are described below. +. +.SS "Defining subpatterns for use by reference only" +.rs +.sp +If the condition is the string (DEFINE), and there is no subpattern with the +name DEFINE, the condition is always false. In this case, there may be only one +alternative in the subpattern. It is always skipped if control reaches this +point in the pattern; the idea of DEFINE is that it can be used to define +"subroutines" that can be referenced from elsewhere. (The use of "subroutines" +is described below.) For example, a pattern to match an IPv4 address could be +written like this (ignore whitespace and line breaks): +.sp + (?(DEFINE) (?<byte> 2[0-4]\ed | 25[0-5] | 1\ed\ed | [1-9]?\ed) ) + \eb (?&byte) (\e.(?&byte)){3} \eb +.sp +The first part of the pattern is a DEFINE group inside which a another group +named "byte" is defined. This matches an individual component of an IPv4 +address (a number less than 256). When matching takes place, this part of the +pattern is skipped because DEFINE acts like a false condition. .P -If the condition is not a sequence of digits or (R), it must be an assertion. +The rest of the pattern uses references to the named group to match the four +dot-separated components of an IPv4 address, insisting on a word boundary at +each end. +. +.SS "Assertion conditions" +.rs +.sp +If the condition is not in any of the above formats, it must be an assertion. This may be a positive or negative lookahead or lookbehind assertion. Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: @@ -1483,28 +1906,34 @@ Consider the problem of matching a string in parentheses, allowing for unlimited nested parentheses. Without the use of recursion, the best that can be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. Perl provides a facility -that allows regular expressions to recurse (amongst other things). It does this -by interpolating Perl code in the expression at run time, and the code can -refer to the expression itself. A Perl pattern to solve the parentheses problem -can be created like this: +is not possible to handle an arbitrary nesting depth. +.P +For some time, Perl has provided a facility that allows regular expressions to +recurse (amongst other things). It does this by interpolating Perl code in the +expression at run time, and the code can refer to the expression itself. A Perl +pattern using code interpolation to solve the parentheses problem can be +created like this: .sp $re = qr{\e( (?: (?>[^()]+) | (?p{$re}) )* \e)}x; .sp The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. Obviously, PCRE cannot support -the interpolation of Perl code. Instead, it supports some special syntax for -recursion of the entire pattern, and also for individual subpattern recursion. -.P -The special item that consists of (? followed by a number greater than zero and -a closing parenthesis is a recursive call of the subpattern of the given -number, provided that it occurs inside that subpattern. (If not, it is a -"subroutine" call, which is described in the next section.) The special item -(?R) is a recursive call of the entire regular expression. -.P -A recursive subpattern call is always treated as an atomic group. That is, once -it has matched some of the subject string, it is never re-entered, even if -it contains untried alternatives and there is a subsequent matching failure. +recursively to the pattern in which it appears. +.P +Obviously, PCRE cannot support the interpolation of Perl code. Instead, it +supports special syntax for recursion of the entire pattern, and also for +individual subpattern recursion. After its introduction in PCRE and Python, +this kind of recursion was introduced into Perl at release 5.10. +.P +A special item that consists of (? followed by a number greater than zero and a +closing parenthesis is a recursive call of the subpattern of the given number, +provided that it occurs inside that subpattern. (If not, it is a "subroutine" +call, which is described in the next section.) The special item (?R) or (?0) is +a recursive call of the entire regular expression. +.P +In PCRE (like Python, but unlike Perl), a recursive subpattern call is always +treated as an atomic group. That is, once it has matched some of the subject +string, it is never re-entered, even if it contains untried alternatives and +there is a subsequent matching failure. .P This PCRE pattern solves the nested parentheses problem (assume the PCRE_EXTENDED option is set so that white space is ignored): @@ -1522,18 +1951,33 @@ ( \e( ( (?>[^()]+) | (?1) )* \e) ) .sp We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. In a larger pattern, keeping track of -parenthesis numbers can be tricky. It may be more convenient to use named -parentheses instead. For this, PCRE uses (?P>name), which is an extension to -the Python syntax that PCRE uses for named parentheses (Perl does not provide -named parentheses). We could rewrite the above example as follows: -.sp - (?P<pn> \e( ( (?>[^()]+) | (?P>pn) )* \e) ) -.sp -This particular example pattern contains nested unlimited repeats, and so the -use of atomic grouping for matching strings of non-parentheses is important -when applying the pattern to strings that do not match. For example, when this -pattern is applied to +them instead of the whole pattern. +.P +In a larger pattern, keeping track of parenthesis numbers can be tricky. This +is made easier by the use of relative references. (A Perl 5.10 feature.) +Instead of (?1) in the pattern above you can write (?-2) to refer to the second +most recently opened parentheses preceding the recursion. In other words, a +negative number counts capturing parentheses leftwards from the point at which +it is encountered. +.P +It is also possible to refer to subsequently opened parentheses, by writing +references such as (?+2). However, these cannot be recursive because the +reference is not inside the parentheses that are referenced. They are always +"subroutine" calls, as described in the next section. +.P +An alternative approach is to use named parentheses instead. The Perl syntax +for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We +could rewrite the above example as follows: +.sp + (?<pn> \e( ( (?>[^()]+) | (?&pn) )* \e) ) +.sp +If there is more than one subpattern with the same name, the earliest one is +used. +.P +This particular example pattern that we have been looking at contains nested +unlimited repeats, and so the use of atomic grouping for matching strings of +non-parentheses is important when applying the pattern to strings that do not +match. For example, when this pattern is applied to .sp (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() .sp @@ -1545,7 +1989,7 @@ At the end of a match, the values set for any capturing subpatterns are those from the outermost level of the recursion at which the subpattern value is set. If you want to obtain intermediate values, a callout function can be used (see -the next section and the +below and the .\" HREF \fBpcrecallout\fP .\" @@ -1584,8 +2028,15 @@ .sp If the syntax for a recursive subpattern reference (either by number or by name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. An earlier example pointed out that the -pattern +subroutine in a programming language. The "called" subpattern may be defined +before or after the reference. A numbered reference can be absolute or +relative, as in these examples: +.sp + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... +.sp +An earlier example pointed out that the pattern .sp (sens|respons)e and \e1ibility .sp @@ -1595,13 +2046,42 @@ (sens|respons)e and (?1)ibility .sp is used, it does match "sense and responsibility" as well as the other two -strings. Such references, if given numerically, must follow the subpattern to -which they refer. However, named references can refer to later subpatterns. +strings. Another example is given in the discussion of DEFINE above. .P Like recursive subpatterns, a "subroutine" call is always treated as an atomic group. That is, once it has matched some of the subject string, it is never re-entered, even if it contains untried alternatives and there is a subsequent matching failure. +.P +When a subpattern is used as a subroutine, processing options such as +case-independence are fixed when the subpattern is defined. They cannot be +changed for different calls. For example, consider this pattern: +.sp + (abc)(?i:(?-1)) +.sp +It matches "abcabc". It does not match "abcABC" because the change of +processing option does not affect the called subpattern. +. +. +.\" HTML <a name="onigurumasubroutines"></a> +.SH "ONIGURUMA SUBROUTINE SYNTAX" +.rs +.sp +For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a subroutine, possibly recursively. Here +are two of the examples used above, rewritten using this syntax: +.sp + (?<pn> \e( ( (?>[^()]+) | \eg<pn> )* \e) ) + (sens|respons)e and \eg'1'ibility +.sp +PCRE supports an extension to Oniguruma: if a number is preceded by a +plus or a minus sign it is taken as a relative reference. For example: +.sp + (abc)(?i:\eg<-1>) +.sp +Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP +synonymous. The former is a back reference; the latter is a subroutine call. . . .SH CALLOUTS @@ -1622,7 +2102,7 @@ can put a number less than 256 after the letter C. The default value is zero. For example, this pattern has two callout points: .sp - (?C1)\dabc(?C2)def + (?C1)abc(?C2)def .sp If the PCRE_AUTO_CALLOUT flag is passed to \fBpcre_compile()\fP, callouts are automatically installed before each item in the pattern. They are all numbered @@ -1638,8 +2118,142 @@ \fBpcrecallout\fP .\" documentation. +. +. +.SH "BACKTRACKING CONTROL" +.rs +.sp +Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which +are described in the Perl documentation as "experimental and subject to change +or removal in a future version of Perl". It goes on to say: "Their usage in +production code should be noted to avoid problems during upgrades." The same +remarks apply to the PCRE features described in this section. +.P +Since these verbs are specifically related to backtracking, most of them can be +used only when the pattern is to be matched using \fBpcre_exec()\fP, which uses +a backtracking algorithm. With the exception of (*FAIL), which behaves like a +failing negative assertion, they cause an error if encountered by +\fBpcre_dfa_exec()\fP. .P -.in 0 -Last updated: 06 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +The new verbs make use of what was previously invalid syntax: an opening +parenthesis followed by an asterisk. In Perl, they are generally of the form +(*VERB:ARG) but PCRE does not support the use of arguments, so its general +form is just (*VERB). Any number of these verbs may occur in a pattern. There +are two kinds: +. +.SS "Verbs that act immediately" +.rs +.sp +The following verbs act as soon as they are encountered: +.sp + (*ACCEPT) +.sp +This verb causes the match to end successfully, skipping the remainder of the +pattern. When inside a recursion, only the innermost pattern is ended +immediately. PCRE differs from Perl in what happens if the (*ACCEPT) is inside +capturing parentheses. In Perl, the data so far is captured: in PCRE no data is +captured. For example: +.sp + A(A|B(*ACCEPT)|C)D +.sp +This matches "AB", "AAD", or "ACD", but when it matches "AB", no data is +captured. +.sp + (*FAIL) or (*F) +.sp +This verb causes the match to fail, forcing backtracking to occur. It is +equivalent to (?!) but easier to read. The Perl documentation notes that it is +probably useful only when combined with (?{}) or (??{}). Those are, of course, +Perl features that are not present in PCRE. The nearest equivalent is the +callout feature, as for example in this pattern: +.sp + a+(?C)(*FAIL) +.sp +A match with the string "aaaa" always fails, but the callout is taken before +each backtrack happens (in this example, 10 times). +. +.SS "Verbs that act after backtracking" +.rs +.sp +The following verbs do nothing when they are encountered. Matching continues +with what follows, but if there is no subsequent match, a failure is forced. +The verbs differ in exactly what kind of failure occurs. +.sp + (*COMMIT) +.sp +This verb causes the whole match to fail outright if the rest of the pattern +does not match. Even if the pattern is unanchored, no further attempts to find +a match by advancing the start point take place. Once (*COMMIT) has been +passed, \fBpcre_exec()\fP is committed to finding a match at the current +starting point, or not at all. For example: +.sp + a+(*COMMIT)b +.sp +This matches "xxaab" but not "aacaab". It can be thought of as a kind of +dynamic anchor, or "I've started, so I must finish." +.sp + (*PRUNE) +.sp +This verb causes the match to fail at the current position if the rest of the +pattern does not match. If the pattern is unanchored, the normal "bumpalong" +advance to the next starting character then happens. Backtracking can occur as +usual to the left of (*PRUNE), or when matching to the right of (*PRUNE), but +if there is no match to the right, backtracking cannot cross (*PRUNE). +In simple cases, the use of (*PRUNE) is just an alternative to an atomic +group or possessive quantifier, but there are some uses of (*PRUNE) that cannot +be expressed in any other way. +.sp + (*SKIP) +.sp +This verb is like (*PRUNE), except that if the pattern is unanchored, the +"bumpalong" advance is not to the next character, but to the position in the +subject where (*SKIP) was encountered. (*SKIP) signifies that whatever text +was matched leading up to it cannot be part of a successful match. Consider: +.sp + a+(*SKIP)b +.sp +If the subject is "aaaac...", after the first match attempt fails (starting at +the first character in the string), the starting point skips on to start the +next attempt at "c". Note that a possessive quantifer does not have the same +effect in this example; although it would suppress backtracking during the +first match attempt, the second attempt would start at the second character +instead of skipping on to "c". +.sp + (*THEN) +.sp +This verb causes a skip to the next alternation if the rest of the pattern does +not match. That is, it cancels pending backtracking, but only within the +current alternation. Its name comes from the observation that it can be used +for a pattern-based if-then-else block: +.sp + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... +.sp +If the COND1 pattern matches, FOO is tried (and possibly further items after +the end of the group if FOO succeeds); on failure the matcher skips to the +second alternative and tries COND2, without backtracking into COND1. If (*THEN) +is used outside of any alternation, it acts exactly like (*PRUNE). +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcreapi\fP(3), \fBpcrecallout\fP(3), \fBpcrematching\fP(3), \fBpcre\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 11 April 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcreperform.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcreperform.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcreperform.3 Mon Jun 8 18:51:30 2009 @@ -4,13 +4,75 @@ .SH "PCRE PERFORMANCE" .rs .sp -Certain items that may appear in regular expression patterns are more efficient +Two aspects of performance are discussed below: memory usage and processing +time. The way you express your pattern as a regular expression can affect both +of them. +. +.SH "MEMORY USAGE" +.rs +.sp +Patterns are compiled by PCRE into a reasonably efficient byte code, so that +most simple patterns do not use much memory. However, there is one case where +memory usage can be unexpectedly large. When a parenthesized subpattern has a +quantifier with a minimum greater than 1 and/or a limited maximum, the whole +subpattern is repeated in the compiled code. For example, the pattern +.sp + (abc|def){2,4} +.sp +is compiled as if it were +.sp + (abc|def)(abc|def)((abc|def)(abc|def)?)? +.sp +(Technical aside: It is done this way so that backtrack points within each of +the repetitions can be independently maintained.) +.P +For regular expressions whose quantifiers use only small numbers, this is not +usually a problem. However, if the numbers are large, and particularly if such +repetitions are nested, the memory usage can become an embarrassment. For +example, the very simple pattern +.sp + ((ab){1,1000}c){1,3} +.sp +uses 51K bytes when compiled. When PCRE is compiled with its default internal +pointer size of two bytes, the size limit on a compiled pattern is 64K, and +this is reached with the above pattern if the outer repetition is increased +from 3 to 4. PCRE can be compiled to use larger internal pointers and thus +handle larger compiled patterns, but it is better to try to rewrite your +pattern to use less memory if you can. +.P +One way of reducing the memory usage for such patterns is to make use of PCRE's +.\" HTML <a href="pcrepattern.html#subpatternsassubroutines"> +.\" </a> +"subroutine" +.\" +facility. Re-writing the above pattern as +.sp + ((ab)(?2){0,999}c)(?1){0,2} +.sp +reduces the memory requirements to 18K, and indeed it remains under 20K even +with the outer repetition increased to 100. However, this pattern is not +exactly equivalent, because the "subroutine" calls are treated as +.\" HTML <a href="pcrepattern.html#atomicgroup"> +.\" </a> +atomic groups +.\" +into which there can be no backtracking if there is a subsequent matching +failure. Therefore, PCRE cannot do this kind of rewriting automatically. +Furthermore, there is a noticeable loss of speed when executing the modified +pattern. Nevertheless, if the atomic grouping is not a problem and the loss of +speed is acceptable, this kind of rewriting will allow you to process patterns +that PCRE cannot otherwise handle. +. +.SH "PROCESSING TIME" +.rs +.sp +Certain items in regular expression patterns are processed more efficiently than others. It is more efficient to use a character class like [aeiou] than a -set of alternatives such as (a|e|i|o|u). In general, the simplest construction -that provides the required behaviour is usually the most efficient. Jeffrey -Friedl's book contains a lot of useful general discussion about optimizing -regular expressions for efficient performance. This document contains a few -observations about PCRE. +set of single-character alternatives such as (a|e|i|o|u). In general, the +simplest construction that provides the required behaviour is usually the most +efficient. Jeffrey Friedl's book contains a lot of useful general discussion +about optimizing regular expressions for efficient performance. This document +contains a few observations about PCRE. .P Using Unicode character properties (the \ep, \eP, and \eX escapes) is slow, because PCRE has to scan a structure that contains data for over fifteen @@ -42,14 +104,15 @@ long time to run when applied to a string that does not match. Consider the pattern fragment .sp - (a+)* + ^(a+)* .sp -This can match "aaaa" in 33 different ways, and this number increases very +This can match "aaaa" in 16 different ways, and this number increases very rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match +times, and for each of those cases other than 0 or 4, the + repeats can match different numbers of times.) When the remainder of the pattern is such that the entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. +variation, and this can take an extremely long time, even for relatively short +strings. .P An optimization catches some of the more simple cases such as .sp @@ -69,8 +132,22 @@ .P In many cases, the solution to this kind of performance issue is to use an atomic group or a possessive quantifier. -.P -.in 0 -Last updated: 28 February 2005 -.br -Copyright (c) 1997-2005 University of Cambridge. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 06 March 2007 +Copyright (c) 1997-2007 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcreposix.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcreposix.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcreposix.3 Mon Jun 8 18:51:30 2009 @@ -7,22 +7,18 @@ .B #include <pcreposix.h> .PP .SM -.br .B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, .ti +5n .B int \fIcflags\fP); .PP -.br .B int regexec(regex_t *\fIpreg\fP, const char *\fIstring\fP, .ti +5n .B size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP); .PP -.br .B size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP, .ti +5n .B char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP); .PP -.br .B void regfree(regex_t *\fIpreg\fP); . .SH DESCRIPTION @@ -43,11 +39,11 @@ command for linking an application that uses them. Because the POSIX functions call the native ones, it is also necessary to add \fB-lpcre\fP. .P -I have implemented only those option bits that can be reasonably mapped to PCRE -native options. In addition, the option REG_EXTENDED is defined with the value -zero. This has no effect, but since programs that are written to the POSIX -interface often use it, this makes it easier to slot in PCRE as a replacement -library. Other POSIX options are not even defined. +I have implemented only those POSIX option bits that can be reasonably mapped +to PCRE native options. In addition, the option REG_EXTENDED is defined with +the value zero. This has no effect, but since programs that are written to the +POSIX interface often use it, this makes it easier to slot in PCRE as a +replacement library. Other POSIX options are not even defined. .P When PCRE is called via these functions, it is only the API that is POSIX-like in style. The syntax and semantics of the regular expressions themselves are @@ -161,18 +157,36 @@ .rs .sp The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP -against a given \fIstring\fP, which is terminated by a zero byte, subject to -the options in \fIeflags\fP. These can be: +against a given \fIstring\fP, which is by default terminated by a zero byte +(but see REG_STARTEND below), subject to the options in \fIeflags\fP. These can +be: .sp REG_NOTBOL .sp The PCRE_NOTBOL option is set when calling the underlying PCRE matching function. .sp + REG_NOTEMPTY +.sp +The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching +function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, +setting this option can give more POSIX-like behaviour in some situations. +.sp REG_NOTEOL .sp The PCRE_NOTEOL option is set when calling the underlying PCRE matching function. +.sp + REG_STARTEND +.sp +The string is considered to start at \fIstring\fP + \fIpmatch[0].rm_so\fP and +to have a terminating NUL located at \fIstring\fP + \fIpmatch[0].rm_eo\fP +(there need not actually be a NUL at that location), regardless of the value of +\fInmatch\fP. This is a BSD extension, compatible with but not specified by +IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software +intended to be portable to other systems. Note that a non-zero \fIrm_so\fP does +not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not +how it is matched. .P If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of @@ -214,13 +228,17 @@ .SH AUTHOR .rs .sp +.nf Philip Hazel -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. -.P -.in 0 -Last updated: 16 January 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 11 March 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcreprecompile.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcreprecompile.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcreprecompile.3 Mon Jun 8 18:51:30 2009 @@ -17,7 +17,9 @@ If you save compiled patterns to a file, you can copy them to a different host and run them there. This works even if the new host has the opposite endianness to the one on which the patterns were compiled. There may be a small -performance penalty, but it should be insignificant. +performance penalty, but it should be insignificant. However, compiling regular +expressions with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes. . . .SH "SAVING A COMPILED PATTERN" @@ -115,17 +117,26 @@ .SH "COMPATIBILITY WITH DIFFERENT PCRE RELEASES" .rs .sp -The layout of the control block that is at the start of the data that makes up -a compiled pattern was changed for release 5.0. If you have any saved patterns -that were compiled with previous releases (not a facility that was previously -advertised), you will have to recompile them for release 5.0. However, from now -on, it should be possible to make changes in a compatible manner. -.P -Notwithstanding the above, if you have any saved patterns in UTF-8 mode that -use \ep or \eP that were compiled with any release up to and including 6.4, you -will have to recompile them for release 6.5 and above. -.P -.in 0 -Last updated: 01 February 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +In general, it is safest to recompile all saved patterns when you update to a +new PCRE release, though not all updates actually require this. Recompiling is +definitely needed for release 7.2. +. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 13 June 2007 +Copyright (c) 1997-2007 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcresample.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcresample.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcresample.3 Mon Jun 8 18:51:30 2009 @@ -59,8 +59,22 @@ -R/usr/local/lib .sp (for example) to the compile command to get round this problem. -.P -.in 0 -Last updated: 09 September 2004 -.br -Copyright (c) 1997-2004 University of Cambridge. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 23 January 2008 +Copyright (c) 1997-2008 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcrestack.3 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcrestack.3 (original) +++ freeswitch/trunk/libs/pcre/doc/pcrestack.3 Mon Jun 8 18:51:30 2009 @@ -52,7 +52,7 @@ required. Consider now this rewritten pattern, which matches exactly the same strings: .sp - ([^<]++|<(?!inet)) + ([^<]++|<(?!inet))+ .sp This uses very much less stack, because runs of characters that do not contain "<" are "swallowed" in one item inside the parentheses. Recursion happens only @@ -61,6 +61,13 @@ backtracking into the runs of non-"<" characters, but that is not related to stack usage. .P +This example shows that one way of avoiding stack problems when matching long +subject strings is to write repeated parenthesized subpatterns to match more +than one character whenever possible. +. +.SS "Compiling PCRE to use heap instead of stack" +.rs +.sp In environments where stack memory is constrained, you might want to compile PCRE to use heap memory instead of stack for remembering back-up points. This makes it run a lot more slowly, however. Details of how to do this are given in @@ -68,27 +75,17 @@ .\" HREF \fBpcrebuild\fP .\" -documentation. -.P -In Unix-like environments, there is not often a problem with the stack, though -the default limit on stack size varies from system to system. Values from 8Mb -to 64Mb are common. You can find your default limit by running the command: -.sp - ulimit -s -.sp -The effect of running out of stack is often SIGSEGV, though sometimes an error -message is given. You can normally increase the limit on stack size by code -such as this: +documentation. When built in this way, instead of using the stack, PCRE obtains +and frees memory by calling the functions that are pointed to by the +\fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP variables. By default, these +point to \fBmalloc()\fP and \fBfree()\fP, but you can replace the pointers to +cause PCRE to use your own functions. Since the block sizes are always the +same, and are always freed in reverse order, it may be possible to implement +customized memory handlers that are more efficient than the standard functions. +. +.SS "Limiting PCRE's stack usage" +.rs .sp - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = 100*1024*1024; - setrlimit(RLIMIT_STACK, &rlim); -.sp -This reads the current limits (soft and hard) using \fBgetrlimit()\fP, then -attempts to increase the soft limit to 100Mb using \fBsetrlimit()\fP. You must -do this before calling \fBpcre_exec()\fP. -.P PCRE has an internal counter that can be used to limit the depth of recursion, and thus cause \fBpcre_exec()\fP to give an error code before it runs out of stack. By default, the limit is very large, and unlikely ever to operate. It @@ -107,9 +104,57 @@ recursion. Thus, if you want to limit your stack usage to 8Mb, you should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can support around 128000 recursions. The \fBpcretest\fP test program has a command -line option (\fB-S\fP) that can be used to increase its stack. -.P -.in 0 -Last updated: 29 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +line option (\fB-S\fP) that can be used to increase the size of its stack. +. +.SS "Changing stack size in Unix-like systems" +.rs +.sp +In Unix-like environments, there is not often a problem with the stack unless +very long strings are involved, though the default limit on stack size varies +from system to system. Values from 8Mb to 64Mb are common. You can find your +default limit by running the command: +.sp + ulimit -s +.sp +Unfortunately, the effect of running out of stack is often SIGSEGV, though +sometimes a more explicit error message is given. You can normally increase the +limit on stack size by code such as this: +.sp + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); +.sp +This reads the current limits (soft and hard) using \fBgetrlimit()\fP, then +attempts to increase the soft limit to 100Mb using \fBsetrlimit()\fP. You must +do this before calling \fBpcre_exec()\fP. +. +.SS "Changing stack size in Mac OS X" +.rs +.sp +Using \fBsetrlimit()\fP, as described above, should also work on Mac OS X. It +is also possible to set a stack size when linking a program. There is a +discussion about stack sizes in Mac OS X at this web site: +.\" HTML <a href="http://developer.apple.com/qa/qa2005/qa1419.html"> +.\" </a> +http://developer.apple.com/qa/qa2005/qa1419.html. +.\" +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 09 July 2008 +Copyright (c) 1997-2008 University of Cambridge. +.fi Added: freeswitch/trunk/libs/pcre/doc/pcresyntax.3 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/doc/pcresyntax.3 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,449 @@ +.TH PCRESYNTAX 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE REGULAR EXPRESSION SYNTAX SUMMARY" +.rs +.sp +The full syntax and semantics of the regular expressions that are supported by +PCRE are described in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. This document contains just a quick-reference summary of the +syntax. +. +. +.SH "QUOTING" +.rs +.sp + \ex where x is non-alphanumeric is a literal x + \eQ...\eE treat enclosed characters as literal +. +. +.SH "CHARACTERS" +.rs +.sp + \ea alarm, that is, the BEL character (hex 07) + \ecx "control-x", where x is any character + \ee escape (hex 1B) + \ef formfeed (hex 0C) + \en newline (hex 0A) + \er carriage return (hex 0D) + \et tab (hex 09) + \eddd character with octal code ddd, or backreference + \exhh character with hex code hh + \ex{hhh..} character with hex code hhh.. +. +. +.SH "CHARACTER TYPES" +.rs +.sp + . any character except newline; + in dotall mode, any character whatsoever + \eC one byte, even in UTF-8 mode (best avoided) + \ed a decimal digit + \eD a character that is not a decimal digit + \eh a horizontal whitespace character + \eH a character that is not a horizontal whitespace character + \ep{\fIxx\fP} a character with the \fIxx\fP property + \eP{\fIxx\fP} a character without the \fIxx\fP property + \eR a newline sequence + \es a whitespace character + \eS a character that is not a whitespace character + \ev a vertical whitespace character + \eV a character that is not a vertical whitespace character + \ew a "word" character + \eW a "non-word" character + \eX an extended Unicode sequence +.sp +In PCRE, \ed, \eD, \es, \eS, \ew, and \eW recognize only ASCII characters. +. +. +.SH "GENERAL CATEGORY PROPERTY CODES FOR \ep and \eP" +.rs +.sp + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate +.sp + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt +.sp + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark +.sp + N Number + Nd Decimal number + Nl Letter number + No Other number +.sp + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation +.sp + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol +.sp + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +. +. +.SH "SCRIPT NAMES FOR \ep AND \eP" +.rs +.sp +Arabic, +Armenian, +Balinese, +Bengali, +Bopomofo, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Inherited, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lycian, +Lydian, +Malayalam, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Saurashtra, +Shavian, +Sinhala, +Sudanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +. +. +.SH "CHARACTER CLASSES" +.rs +.sp + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set +.sp + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space whitespace + upper upper case letter + word same as \ew + xdigit hexadecimal digit +.sp +In PCRE, POSIX character set names recognize only ASCII characters. You can use +\eQ...\eE inside a character class. +. +. +.SH "QUANTIFIERS" +.rs +.sp + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy +. +. +.SH "ANCHORS AND SIMPLE ASSERTIONS" +.rs +.sp + \eb word boundary (only ASCII letters recognized) + \eB not a word boundary + ^ start of subject + also after internal newline in multiline mode + \eA start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \eZ end of subject + also before newline at end of subject + \ez end of subject + \eG first matching position in subject +. +. +.SH "MATCH POINT RESET" +.rs +.sp + \eK reset start of match +. +. +.SH "ALTERNATION" +.rs +.sp + expr|expr|expr... +. +. +.SH "CAPTURING" +.rs +.sp + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative +. +. +.SH "ATOMIC GROUPS" +.rs +.sp + (?>...) atomic, non-capturing group +. +. +. +. +.SH "COMMENT" +.rs +.sp + (?#....) comment (not nestable) +. +. +.SH "OPTION SETTING" +.rs +.sp + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) +.sp +The following is recognized only at the start of a pattern or after one of the +newline-setting options with similar syntax: +.sp + (*UTF8) set UTF-8 mode +. +. +.SH "LOOKAHEAD AND LOOKBEHIND ASSERTIONS" +.rs +.sp + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind +.sp +Each top-level branch of a look behind must be of a fixed length. +. +. +.SH "BACKREFERENCES" +.rs +.sp + \en reference by number (can be ambiguous) + \egn reference by number + \eg{n} reference by number + \eg{-n} relative reference by number + \ek<name> reference by name (Perl) + \ek'name' reference by name (Perl) + \eg{name} reference by name (Perl) + \ek{name} reference by name (.NET) + (?P=name) reference by name (Python) +. +. +.SH "SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)" +.rs +.sp + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \eg<name> call subpattern by name (Oniguruma) + \eg'name' call subpattern by name (Oniguruma) + \eg<n> call subpattern by absolute number (Oniguruma) + \eg'n' call subpattern by absolute number (Oniguruma) + \eg<+n> call subpattern by relative number (PCRE extension) + \eg'+n' call subpattern by relative number (PCRE extension) + \eg<-n> call subpattern by relative number (PCRE extension) + \eg'-n' call subpattern by relative number (PCRE extension) +. +. +.SH "CONDITIONAL PATTERNS" +.rs +.sp + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) +.sp + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition +. +. +.SH "BACKTRACKING CONTROL" +.rs +.sp +The following act immediately they are reached: +.sp + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) +.sp +The following act only when a subsequent match failure causes a backtrack to +reach them. They all force a match failure, but they differ in what happens +afterwards. Those that advance the start-of-match point do so only if the +pattern is not anchored. +.sp + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*SKIP) advance start to current matching position + (*THEN) local failure, backtrack to next alternation +. +. +.SH "NEWLINE CONVENTIONS" +.rs +.sp +These are recognized only at the very start of the pattern or after a +(*BSR_...) or (*UTF8) option. +.sp + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence +. +. +.SH "WHAT \eR MATCHES" +.rs +.sp +These are recognized only at the very start of the pattern or after a +(*...) option that sets the newline convention or UTF-8 mode. +.sp + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence +. +. +.SH "CALLOUTS" +.rs +.sp + (?C) callout + (?Cn) callout with data n +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcrepattern\fP(3), \fBpcreapi\fP(3), \fBpcrecallout\fP(3), +\fBpcrematching\fP(3), \fBpcre\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 11 April 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcretest.1 ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcretest.1 (original) +++ freeswitch/trunk/libs/pcre/doc/pcretest.1 Mon Jun 8 18:51:30 2009 @@ -24,23 +24,36 @@ .SH OPTIONS .rs .TP 10 +\fB-b\fP +Behave as if each regex has the \fB/B\fP (show bytecode) modifier; the internal +form is output after compilation. +.TP 10 \fB-C\fP Output the version number of the PCRE library, and all available information about the optional features that are included, and then exit. .TP 10 \fB-d\fP Behave as if each regex has the \fB/D\fP (debug) modifier; the internal -form is output after compilation. +form and information about the compiled pattern is output after compilation; +\fB-d\fP is equivalent to \fB-b -i\fP. .TP 10 \fB-dfa\fP Behave as if each data line contains the \eD escape sequence; this causes the alternative matching function, \fBpcre_dfa_exec()\fP, to be used instead of the standard \fBpcre_exec()\fP function (more detail is given below). .TP 10 +\fB-help\fP +Output a brief summary these options and then exit. +.TP 10 \fB-i\fP Behave as if each regex has the \fB/I\fP modifier; information about the compiled pattern is given after compilation. .TP 10 +\fB-M\fP +Behave as if each data line contains the \eM escape sequence; this causes +PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by +calling \fBpcre_exec()\fP repeatedly with different limits. +.TP 10 \fB-m\fP Output the size of each compiled pattern after it has been compiled. This is equivalent to adding \fB/M\fP to each regular expression. For compatibility @@ -48,9 +61,11 @@ .TP 10 \fB-o\fP \fIosize\fP Set the number of elements in the output vector that is used when calling -\fBpcre_exec()\fP to be \fIosize\fP. The default value is 45, which is enough -for 14 capturing subexpressions. The vector size can be changed for individual -matching calls by including \eO in the data line (see below). +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP to be \fIosize\fP. The default value +is 45, which is enough for 14 capturing subexpressions for \fBpcre_exec()\fP or +22 different matches for \fBpcre_dfa_exec()\fP. The vector size can be +changed for individual matching calls by including \eO in the data line (see +below). .TP 10 \fB-p\fP Behave as if each regex has the \fB/P\fP modifier; the POSIX wrapper API is @@ -68,7 +83,14 @@ Run each compile, study, and match many times with a timer, and output resulting time per compile or match (in milliseconds). Do not set \fB-m\fP with \fB-t\fP, because you will then get the size output a zillion times, and the -timing will be distorted. +timing will be distorted. You can control the number of iterations that are +used for timing by following \fB-t\fP with a number (as a separate item on the +command line). For example, "-t 1000" would iterate 1000 times. The default is +to iterate 500000 times. +.TP 10 +\fB-tm\fP +This is like \fB-t\fP except that it times only the matching phase, not the +compile or study phases. . . .SH DESCRIPTION @@ -80,14 +102,20 @@ stdout, and prompts for each line of input, using "re>" to prompt for regular expressions, and "data>" to prompt for data lines. .P +When \fBpcretest\fP is built, a configuration option can specify that it should +be linked with the \fBlibreadline\fP library. When this is done, if the input +is from a terminal, it is read using the \fBreadline()\fP function. This +provides line-editing and history facilities. The output from the \fB-help\fP +option states whether or not \fBreadline()\fP will be used. +.P The program handles any number of sets of input on a single input file. Each set starts with a regular expression, and continues with any number of data lines to be matched against the pattern. .P Each data line is matched separately and independently. If you want to do multi-line matches, you have to use the \en escape sequence (or \er or \er\en, -depending on the newline setting) in a single line of input to encode the -newline characters. There is no limit on the length of data lines; the input +etc., depending on the newline setting) in a single line of input to encode the +newline sequences. There is no limit on the length of data lines; the input buffer is automatically extended if it is too small. .P An empty line signals the end of the data lines, at which point a new regular @@ -140,20 +168,30 @@ The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: .sp - \fB/A\fP PCRE_ANCHORED - \fB/C\fP PCRE_AUTO_CALLOUT - \fB/E\fP PCRE_DOLLAR_ENDONLY - \fB/f\fP PCRE_FIRSTLINE - \fB/J\fP PCRE_DUPNAMES - \fB/N\fP PCRE_NO_AUTO_CAPTURE - \fB/U\fP PCRE_UNGREEDY - \fB/X\fP PCRE_EXTRA - \fB/<cr>\fP PCRE_NEWLINE_CR - \fB/<lf>\fP PCRE_NEWLINE_LF - \fB/<crlf>\fP PCRE_NEWLINE_CRLF + \fB/A\fP PCRE_ANCHORED + \fB/C\fP PCRE_AUTO_CALLOUT + \fB/E\fP PCRE_DOLLAR_ENDONLY + \fB/f\fP PCRE_FIRSTLINE + \fB/J\fP PCRE_DUPNAMES + \fB/N\fP PCRE_NO_AUTO_CAPTURE + \fB/U\fP PCRE_UNGREEDY + \fB/X\fP PCRE_EXTRA + \fB/<JS>\fP PCRE_JAVASCRIPT_COMPAT + \fB/<cr>\fP PCRE_NEWLINE_CR + \fB/<lf>\fP PCRE_NEWLINE_LF + \fB/<crlf>\fP PCRE_NEWLINE_CRLF + \fB/<anycrlf>\fP PCRE_NEWLINE_ANYCRLF + \fB/<any>\fP PCRE_NEWLINE_ANY + \fB/<bsr_anycrlf>\fP PCRE_BSR_ANYCRLF + \fB/<bsr_unicode>\fP PCRE_BSR_UNICODE +.sp +Those specifying line ending sequences are literal strings as shown, but the +letters can be in either case. This example sets multiline matching with CRLF +as the line ending sequence: +.sp + /^abc/m<crlf> .sp -Those specifying line endings are literal strings as shown. Details of the -meanings of these PCRE options are given in the +Details of the meanings of these PCRE options are given in the .\" HREF \fBpcreapi\fP .\" @@ -191,6 +229,13 @@ the subject string. This is useful for tests where the subject contains multiple copies of the same substring. .P +The \fB/B\fP modifier is a debugging feature. It requests that \fBpcretest\fP +output a representation of the compiled byte code after compilation. Normally +this information contains length and offset values; however, if \fB/Z\fP is +also present, this data is replaced by spaces. This is a special feature for +use in the automatic test scripts; it ensures that the same output is generated +for different internal link sizes. +.P The \fB/L\fP modifier must be followed directly by the name of a locale, for example, .sp @@ -207,10 +252,8 @@ so on). It does this by calling \fBpcre_fullinfo()\fP after compiling a pattern. If the pattern is studied, the results of that are also output. .P -The \fB/D\fP modifier is a PCRE debugging feature, which also assumes \fB/I\fP. -It causes the internal form of compiled regular expressions to be output after -compilation. If the pattern was studied, the information returned is also -output. +The \fB/D\fP modifier is a PCRE debugging feature, and is equivalent to +\fB/BI\fP, that is, both the \fB/B\fP and the \fB/I\fP modifiers. .P The \fB/F\fP modifier causes \fBpcretest\fP to flip the byte order of the fields in the compiled pattern that contain 2-byte and 4-byte numbers. This @@ -254,17 +297,17 @@ expressions, you probably don't need any of these. The following escapes are recognized: .sp - \ea alarm (= BEL) - \eb backspace - \ee escape - \ef formfeed - \en newline + \ea alarm (BEL, \ex07) + \eb backspace (\ex08) + \ee escape (\ex27) + \ef formfeed (\ex0c) + \en newline (\ex0a) .\" JOIN \eqdd set the PCRE_MATCH_LIMIT limit to dd (any number of digits) - \er carriage return - \et tab - \ev vertical tab + \er carriage return (\ex0d) + \et tab (\ex09) + \ev vertical tab (\ex0b) \ennn octal character (up to 3 octal digits) \exhh hexadecimal character (up to 2 hex digits) .\" JOIN @@ -344,11 +387,20 @@ .\" JOIN \e<crlf> pass the PCRE_NEWLINE_CRLF option to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP +.\" JOIN + \e<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \e<any> pass the PCRE_NEWLINE_ANY option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP .sp -The escapes that specify line endings are literal strings, exactly as shown. -A backslash followed by anything else just escapes the anything else. If the -very last character is a backslash, it is ignored. This gives a way of passing -an empty line as data, since a real empty line terminates the data input. +The escapes that specify line ending sequences are literal strings, exactly as +shown. No more than one newline setting should be present in any data line. +.P +A backslash followed by anything else just escapes the anything else. If +the very last character is a backslash, it is ignored. This gives a way of +passing an empty line as data, since a real empty line terminates the data +input. .P If \eM is present, \fBpcretest\fP calls \fBpcre_exec()\fP several times, with different values in the \fImatch_limit\fP and \fImatch_limit_recursion\fP @@ -374,7 +426,10 @@ The use of \ex{hh...} to represent UTF-8 characters is not dependent on the use of the \fB/8\fP modifier on the pattern. It is recognized always. There may be any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the UTF-8 rules. +six bytes, encoded according to the original UTF-8 rules of RFC 2279. This +allows for values in the range 0 to 0x7FFFFFFF. Note that not all of those are +valid Unicode code points, or indeed valid UTF-8 characters according to the +later rules in RFC 3629. . . .SH "THE ALTERNATIVE MATCHING FUNCTION" @@ -411,7 +466,7 @@ of an interactive \fBpcretest\fP run. .sp $ pcretest - PCRE version 5.00 07-Sep-2004 + PCRE version 7.0 30-Nov-2006 .sp re> /^abc(\ed+)/ data> abc123 @@ -420,11 +475,26 @@ data> xyz No match .sp +Note that unset capturing substrings that are not followed by one that is set +are not returned by \fBpcre_exec()\fP, and are not shown by \fBpcretest\fP. In +the following example, there are two capturing substrings, but when the first +data line is matched, the second, unset substring is not shown. An "internal" +unset substring is shown as "<unset>", as for the second data line. +.sp + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b +.sp If the strings contain any non-printing characters, they are output as \e0x escapes, or as \ex{...} escapes if the \fB/8\fP modifier was present on the -pattern. If the pattern has the \fB/+\fP modifier, the output for substring 0 -is followed by the the rest of the subject string, identified by "0+" like -this: +pattern. See below for the definition of non-printing characters. If the +pattern has the \fB/+\fP modifier, the output for substring 0 is followed by +the the rest of the subject string, identified by "0+" like this: .sp re> /cat/+ data> cataract @@ -452,10 +522,11 @@ length (that is, the return from the extraction function) is given in parentheses after each string for \fB\eC\fP and \fB\eG\fP. .P -Note that while patterns can be continued over several lines (a plain ">" +Note that whereas patterns can be continued over several lines (a plain ">" prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \en escape (or \er or \er\en for those newline -settings). +included in data by means of the \en escape (or \er, \er\en, etc., depending on +the newline sequence setting). +. . . .SH "OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION" @@ -475,7 +546,7 @@ (Using the normal matching function on this data finds only "tang".) The longest matching string is always given first (and numbered zero). .P -If \fB/g\P is present on the pattern, the search for further matches resumes +If \fB/g\fP is present on the pattern, the search for further matches resumes at the end of the longest match. For example: .sp re> /(tang|tangerine|tan)/g @@ -499,7 +570,7 @@ match with additional subject data by means of the \eR escape sequence. For example: .sp - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ data> 23ja\eP\eD Partial match: 23ja data> n05\eR\eD @@ -556,6 +627,21 @@ documentation. . . +. +.SH "NON-PRINTING CHARACTERS" +.rs +.sp +When \fBpcretest\fP is outputting text in the compiled version of a pattern, +bytes other than 32-126 are always treated as non-printing characters are are +therefore shown as hex escapes. +.P +When \fBpcretest\fP is outputting text that is a matched part of a subject +string, it behaves in the same way, unless a different locale has been set for +the pattern (using the \fB/L\fP modifier). In this case, the \fBisprint()\fP +function to distinguish printing and non-printing characters. +. +. +. .SH "SAVING AND RELOADING COMPILED PATTERNS" .rs .sp @@ -616,16 +702,27 @@ result is undefined. . . +.SH "SEE ALSO" +.rs +.sp +\fBpcre\fP(3), \fBpcreapi\fP(3), \fBpcrecallout\fP(3), \fBpcrematching\fP(3), +\fBpcrepartial\fP(d), \fBpcrepattern\fP(3), \fBpcreprecompile\fP(3). +. +. .SH AUTHOR .rs .sp +.nf Philip Hazel -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. -.P -.in 0 -Last updated: 29 June 2006 -.br -Copyright (c) 1997-2006 University of Cambridge. +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 10 March 2009 +Copyright (c) 1997-2009 University of Cambridge. +.fi Modified: freeswitch/trunk/libs/pcre/doc/pcretest.txt ============================================================================== --- freeswitch/trunk/libs/pcre/doc/pcretest.txt (original) +++ freeswitch/trunk/libs/pcre/doc/pcretest.txt Mon Jun 8 18:51:30 2009 @@ -19,67 +19,93 @@ OPTIONS + -b Behave as if each regex has the /B (show bytecode) modifier; + the internal form is output after compilation. + -C Output the version number of the PCRE library, and all avail- - able information about the optional features that are + able information about the optional features that are included, and then exit. - -d Behave as if each regex has the /D (debug) modifier; the - internal form is output after compilation. + -d Behave as if each regex has the /D (debug) modifier; the + internal form and information about the compiled pattern is + output after compilation; -d is equivalent to -b -i. -dfa Behave as if each data line contains the \D escape sequence; this causes the alternative matching function, pcre_dfa_exec(), to be used instead of the standard pcre_exec() function (more detail is given below). + -help Output a brief summary these options and then exit. + -i Behave as if each regex has the /I modifier; information about the compiled pattern is given after compilation. - -m Output the size of each compiled pattern after it has been - compiled. This is equivalent to adding /M to each regular - expression. For compatibility with earlier versions of + -M Behave as if each data line contains the \M escape sequence; + this causes PCRE to discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings by calling pcre_exec() repeat- + edly with different limits. + + -m Output the size of each compiled pattern after it has been + compiled. This is equivalent to adding /M to each regular + expression. For compatibility with earlier versions of pcretest, -s is a synonym for -m. - -o osize Set the number of elements in the output vector that is used - when calling pcre_exec() to be osize. The default value is - 45, which is enough for 14 capturing subexpressions. The vec- - tor size can be changed for individual matching calls by - including \O in the data line (see below). + -o osize Set the number of elements in the output vector that is used + when calling pcre_exec() or pcre_dfa_exec() to be osize. The + default value is 45, which is enough for 14 capturing subex- + pressions for pcre_exec() or 22 different matches for + pcre_dfa_exec(). The vector size can be changed for individ- + ual matching calls by including \O in the data line (see + below). - -p Behave as if each regex has the /P modifier; the POSIX wrap- - per API is used to call PCRE. None of the other options has + -p Behave as if each regex has the /P modifier; the POSIX wrap- + per API is used to call PCRE. None of the other options has any effect when -p is set. - -q Do not output the version number of pcretest at the start of + -q Do not output the version number of pcretest at the start of execution. - -S size On Unix-like systems, set the size of the runtime stack to + -S size On Unix-like systems, set the size of the runtime stack to size megabytes. - -t Run each compile, study, and match many times with a timer, - and output resulting time per compile or match (in millisec- - onds). Do not set -m with -t, because you will then get the - size output a zillion times, and the timing will be dis- - torted. + -t Run each compile, study, and match many times with a timer, + and output resulting time per compile or match (in millisec- + onds). Do not set -m with -t, because you will then get the + size output a zillion times, and the timing will be dis- + torted. You can control the number of iterations that are + used for timing by following -t with a number (as a separate + item on the command line). For example, "-t 1000" would iter- + ate 1000 times. The default is to iterate 500000 times. + + -tm This is like -t except that it times only the matching phase, + not the compile or study phases. DESCRIPTION - If pcretest is given two filename arguments, it reads from the first + If pcretest is given two filename arguments, it reads from the first and writes to the second. If it is given only one filename argument, it - reads from that file and writes to stdout. Otherwise, it reads from - stdin and writes to stdout, and prompts for each line of input, using + reads from that file and writes to stdout. Otherwise, it reads from + stdin and writes to stdout, and prompts for each line of input, using "re>" to prompt for regular expressions, and "data>" to prompt for data lines. + When pcretest is built, a configuration option can specify that it + should be linked with the libreadline library. When this is done, if + the input is from a terminal, it is read using the readline() function. + This provides line-editing and history facilities. The output from the + -help option states whether or not readline() will be used. + The program handles any number of sets of input on a single input file. - Each set starts with a regular expression, and continues with any num- + Each set starts with a regular expression, and continues with any num- ber of data lines to be matched against the pattern. - Each data line is matched separately and independently. If you want to + Each data line is matched separately and independently. If you want to do multi-line matches, you have to use the \n escape sequence (or \r or - \r\n, depending on the newline setting) in a single line of input to - encode the newline characters. There is no limit on the length of data - lines; the input buffer is automatically extended if it is too small. + \r\n, etc., depending on the newline setting) in a single line of input + to encode the newline sequences. There is no limit on the length of + data lines; the input buffer is automatically extended if it is too + small. An empty line signals the end of the data lines, at which point a new regular expression is read. The regular expressions are given enclosed @@ -131,39 +157,49 @@ The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: - /A PCRE_ANCHORED - /C PCRE_AUTO_CALLOUT - /E PCRE_DOLLAR_ENDONLY - /f PCRE_FIRSTLINE - /J PCRE_DUPNAMES - /N PCRE_NO_AUTO_CAPTURE - /U PCRE_UNGREEDY - /X PCRE_EXTRA - /<cr> PCRE_NEWLINE_CR - /<lf> PCRE_NEWLINE_LF - /<crlf> PCRE_NEWLINE_CRLF - - Those specifying line endings are literal strings as shown. Details of - the meanings of these PCRE options are given in the pcreapi documenta- - tion. + /A PCRE_ANCHORED + /C PCRE_AUTO_CALLOUT + /E PCRE_DOLLAR_ENDONLY + /f PCRE_FIRSTLINE + /J PCRE_DUPNAMES + /N PCRE_NO_AUTO_CAPTURE + /U PCRE_UNGREEDY + /X PCRE_EXTRA + /<JS> PCRE_JAVASCRIPT_COMPAT + /<cr> PCRE_NEWLINE_CR + /<lf> PCRE_NEWLINE_LF + /<crlf> PCRE_NEWLINE_CRLF + /<anycrlf> PCRE_NEWLINE_ANYCRLF + /<any> PCRE_NEWLINE_ANY + /<bsr_anycrlf> PCRE_BSR_ANYCRLF + /<bsr_unicode> PCRE_BSR_UNICODE + + Those specifying line ending sequences are literal strings as shown, + but the letters can be in either case. This example sets multiline + matching with CRLF as the line ending sequence: + + /^abc/m<crlf> + + Details of the meanings of these PCRE options are given in the pcreapi + documentation. Finding all matches in a string - Searching for all possible matches within each subject string can be - requested by the /g or /G modifier. After finding a match, PCRE is + Searching for all possible matches within each subject string can be + requested by the /g or /G modifier. After finding a match, PCRE is called again to search the remainder of the subject string. The differ- ence between /g and /G is that the former uses the startoffset argument - to pcre_exec() to start searching at a new point within the entire - string (which is in effect what Perl does), whereas the latter passes - over a shortened substring. This makes a difference to the matching + to pcre_exec() to start searching at a new point within the entire + string (which is in effect what Perl does), whereas the latter passes + over a shortened substring. This makes a difference to the matching process if the pattern begins with a lookbehind assertion (including \b or \B). - If any call to pcre_exec() in a /g or /G sequence matches an empty - string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED - flags set in order to search for another, non-empty, match at the same - point. If this second match fails, the start offset is advanced by - one, and the normal match is retried. This imitates the way Perl han- + If any call to pcre_exec() in a /g or /G sequence matches an empty + string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED + flags set in order to search for another, non-empty, match at the same + point. If this second match fails, the start offset is advanced by + one, and the normal match is retried. This imitates the way Perl han- dles such cases when using the /g modifier or the split() function. Other modifiers @@ -175,38 +211,43 @@ remainder of the subject string. This is useful for tests where the subject contains multiple copies of the same substring. - The /L modifier must be followed directly by the name of a locale, for + The /B modifier is a debugging feature. It requests that pcretest out- + put a representation of the compiled byte code after compilation. Nor- + mally this information contains length and offset values; however, if + /Z is also present, this data is replaced by spaces. This is a special + feature for use in the automatic test scripts; it ensures that the same + output is generated for different internal link sizes. + + The /L modifier must be followed directly by the name of a locale, for example, /pattern/Lfr_FR For this reason, it must be the last modifier. The given locale is set, - pcre_maketables() is called to build a set of character tables for the - locale, and this is then passed to pcre_compile() when compiling the - regular expression. Without an /L modifier, NULL is passed as the - tables pointer; that is, /L applies only to the expression on which it + pcre_maketables() is called to build a set of character tables for the + locale, and this is then passed to pcre_compile() when compiling the + regular expression. Without an /L modifier, NULL is passed as the + tables pointer; that is, /L applies only to the expression on which it appears. - The /I modifier requests that pcretest output information about the - compiled pattern (whether it is anchored, has a fixed first character, - and so on). It does this by calling pcre_fullinfo() after compiling a - pattern. If the pattern is studied, the results of that are also out- + The /I modifier requests that pcretest output information about the + compiled pattern (whether it is anchored, has a fixed first character, + and so on). It does this by calling pcre_fullinfo() after compiling a + pattern. If the pattern is studied, the results of that are also out- put. - The /D modifier is a PCRE debugging feature, which also assumes /I. It - causes the internal form of compiled regular expressions to be output - after compilation. If the pattern was studied, the information returned - is also output. + The /D modifier is a PCRE debugging feature, and is equivalent to /BI, + that is, both the /B and the /I modifiers. The /F modifier causes pcretest to flip the byte order of the fields in - the compiled pattern that contain 2-byte and 4-byte numbers. This - facility is for testing the feature in PCRE that allows it to execute + the compiled pattern that contain 2-byte and 4-byte numbers. This + facility is for testing the feature in PCRE that allows it to execute patterns that were compiled on a host with a different endianness. This - feature is not available when the POSIX interface to PCRE is being - used, that is, when the /P pattern modifier is specified. See also the + feature is not available when the POSIX interface to PCRE is being + used, that is, when the /P pattern modifier is specified. See also the section about saving and reloading compiled patterns below. - The /S modifier causes pcre_study() to be called after the expression + The /S modifier causes pcre_study() to be called after the expression has been compiled, and the results used when the expression is matched. The /M modifier causes the size of memory block used to hold the com- @@ -216,38 +257,38 @@ rather than its native API. When this is done, all other modifiers except /i, /m, and /+ are ignored. REG_ICASE is set if /i is present, and REG_NEWLINE is set if /m is present. The wrapper functions force - PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. + PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. - The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option - set. This turns on support for UTF-8 character handling in PCRE, pro- - vided that it was compiled with this support enabled. This modifier + The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option + set. This turns on support for UTF-8 character handling in PCRE, pro- + vided that it was compiled with this support enabled. This modifier also causes any non-printing characters in output strings to be printed using the \x{hh...} notation if they are valid UTF-8 sequences. - If the /? modifier is used with /8, it causes pcretest to call - pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the + If the /? modifier is used with /8, it causes pcretest to call + pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the checking of the string for UTF-8 validity. DATA LINES - Before each data line is passed to pcre_exec(), leading and trailing - whitespace is removed, and it is then scanned for \ escapes. Some of - these are pretty esoteric features, intended for checking out some of - the more complicated features of PCRE. If you are just testing "ordi- - nary" regular expressions, you probably don't need any of these. The + Before each data line is passed to pcre_exec(), leading and trailing + whitespace is removed, and it is then scanned for \ escapes. Some of + these are pretty esoteric features, intended for checking out some of + the more complicated features of PCRE. If you are just testing "ordi- + nary" regular expressions, you probably don't need any of these. The following escapes are recognized: - \a alarm (= BEL) - \b backspace - \e escape - \f formfeed - \n newline + \a alarm (BEL, \x07) + \b backspace (\x08) + \e escape (\x27) + \f formfeed (\x0c) + \n newline (\x0a) \qdd set the PCRE_MATCH_LIMIT limit to dd (any number of digits) - \r carriage return - \t tab - \v vertical tab + \r carriage return (\x0d) + \t tab (\x09) + \v vertical tab (\x0b) \nnn octal character (up to 3 octal digits) \xhh hexadecimal character (up to 2 hex digits) \x{hh...} hexadecimal character, any number of digits @@ -304,12 +345,19 @@ or pcre_dfa_exec() \<crlf> pass the PCRE_NEWLINE_CRLF option to pcre_exec() or pcre_dfa_exec() + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre_exec() + or pcre_dfa_exec() + \<any> pass the PCRE_NEWLINE_ANY option to pcre_exec() + or pcre_dfa_exec() - The escapes that specify line endings are literal strings, exactly as - shown. A backslash followed by anything else just escapes the anything - else. If the very last character is a backslash, it is ignored. This - gives a way of passing an empty line as data, since a real empty line - terminates the data input. + The escapes that specify line ending sequences are literal strings, + exactly as shown. No more than one newline setting should be present in + any data line. + + A backslash followed by anything else just escapes the anything else. + If the very last character is a backslash, it is ignored. This gives a + way of passing an empty line as data, since a real empty line termi- + nates the data input. If \M is present, pcretest calls pcre_exec() several times, with dif- ferent values in the match_limit and match_limit_recursion fields of @@ -335,38 +383,42 @@ The use of \x{hh...} to represent UTF-8 characters is not dependent on the use of the /8 modifier on the pattern. It is recognized always. There may be any number of hexadecimal digits inside the braces. The - result is from one to six bytes, encoded according to the UTF-8 rules. + result is from one to six bytes, encoded according to the original + UTF-8 rules of RFC 2279. This allows for values in the range 0 to + 0x7FFFFFFF. Note that not all of those are valid Unicode code points, + or indeed valid UTF-8 characters according to the later rules in RFC + 3629. THE ALTERNATIVE MATCHING FUNCTION - By default, pcretest uses the standard PCRE matching function, + By default, pcretest uses the standard PCRE matching function, pcre_exec() to match each data line. From release 6.0, PCRE supports an - alternative matching function, pcre_dfa_test(), which operates in a - different way, and has some restrictions. The differences between the + alternative matching function, pcre_dfa_test(), which operates in a + different way, and has some restrictions. The differences between the two functions are described in the pcrematching documentation. - If a data line contains the \D escape sequence, or if the command line - contains the -dfa option, the alternative matching function is called. + If a data line contains the \D escape sequence, or if the command line + contains the -dfa option, the alternative matching function is called. This function finds all possible matches at a given point. If, however, - the \F escape sequence is present in the data line, it stops after the + the \F escape sequence is present in the data line, it stops after the first match is found. This is always the shortest possible match. DEFAULT OUTPUT FROM PCRETEST - This section describes the output when the normal matching function, + This section describes the output when the normal matching function, pcre_exec(), is being used. When a match succeeds, pcretest outputs the list of captured substrings - that pcre_exec() returns, starting with number 0 for the string that + that pcre_exec() returns, starting with number 0 for the string that matched the whole pattern. Otherwise, it outputs "No match" or "Partial - match" when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PAR- - TIAL, respectively, and otherwise the PCRE negative error number. Here + match" when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PAR- + TIAL, respectively, and otherwise the PCRE negative error number. Here is an example of an interactive pcretest run. $ pcretest - PCRE version 5.00 07-Sep-2004 + PCRE version 7.0 30-Nov-2006 re> /^abc(\d+)/ data> abc123 @@ -375,18 +427,35 @@ data> xyz No match + Note that unset capturing substrings that are not followed by one that + is set are not returned by pcre_exec(), and are not shown by pcretest. + In the following example, there are two capturing substrings, but when + the first data line is matched, the second, unset substring is not + shown. An "internal" unset substring is shown as "<unset>", as for the + second data line. + + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b + If the strings contain any non-printing characters, they are output as \0x escapes, or as \x{...} escapes if the /8 modifier was present on - the pattern. If the pattern has the /+ modifier, the output for sub- - string 0 is followed by the the rest of the subject string, identified - by "0+" like this: + the pattern. See below for the definition of non-printing characters. + If the pattern has the /+ modifier, the output for substring 0 is fol- + lowed by the the rest of the subject string, identified by "0+" like + this: re> /cat/+ data> cataract 0: cat 0+ aract - If the pattern has the /g or /G modifier, the results of successive + If the pattern has the /g or /G modifier, the results of successive matching attempts are output in sequence, like this: re> /\Bi(\w\w)/g @@ -400,24 +469,24 @@ "No match" is output only if the first match attempt fails. - If any of the sequences \C, \G, or \L are present in a data line that - is successfully matched, the substrings extracted by the convenience + If any of the sequences \C, \G, or \L are present in a data line that + is successfully matched, the substrings extracted by the convenience functions are output with C, G, or L after the string number instead of a colon. This is in addition to the normal full list. The string length - (that is, the return from the extraction function) is given in paren- + (that is, the return from the extraction function) is given in paren- theses after each string for \C and \G. - Note that while patterns can be continued over several lines (a plain + Note that whereas patterns can be continued over several lines (a plain ">" prompt is used for continuations), data lines may not. However new- - lines can be included in data by means of the \n escape (or \r or \r\n - for those newline settings). + lines can be included in data by means of the \n escape (or \r, \r\n, + etc., depending on the newline sequence setting). OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION - When the alternative matching function, pcre_dfa_exec(), is used (by - means of the \D escape sequence or the -dfa command line option), the - output consists of a list of all the matches that start at the first + When the alternative matching function, pcre_dfa_exec(), is used (by + means of the \D escape sequence or the -dfa command line option), the + output consists of a list of all the matches that start at the first point in the subject where there is at least one match. For example: re> /(tang|tangerine|tan)/ @@ -426,11 +495,11 @@ 1: tang 2: tan - (Using the normal matching function on this data finds only "tang".) - The longest matching string is always given first (and numbered zero). + (Using the normal matching function on this data finds only "tang".) + The longest matching string is always given first (and numbered zero). - If /gP is present on the pattern, the search for further matches - resumes at the end of the longest match. For example: + If /g is present on the pattern, the search for further matches resumes + at the end of the longest match. For example: re> /(tang|tangerine|tan)/g data> yellow tangerine and tangy sultana\D @@ -453,7 +522,7 @@ can restart the match with additional subject data by means of the \R escape sequence. For example: - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 23ja\P\D Partial match: 23ja data> n05\R\D @@ -503,67 +572,88 @@ the pcrecallout documentation. +NON-PRINTING CHARACTERS + + When pcretest is outputting text in the compiled version of a pattern, + bytes other than 32-126 are always treated as non-printing characters + are are therefore shown as hex escapes. + + When pcretest is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the /L modifier). In this case, the + isprint() function to distinguish printing and non-printing characters. + + SAVING AND RELOADING COMPILED PATTERNS - The facilities described in this section are not available when the + The facilities described in this section are not available when the POSIX inteface to PCRE is being used, that is, when the /P pattern mod- ifier is specified. When the POSIX interface is not in use, you can cause pcretest to write - a compiled pattern to a file, by following the modifiers with > and a + a compiled pattern to a file, by following the modifiers with > and a file name. For example: /pattern/im >/some/file - See the pcreprecompile documentation for a discussion about saving and + See the pcreprecompile documentation for a discussion about saving and re-using compiled patterns. - The data that is written is binary. The first eight bytes are the - length of the compiled pattern data followed by the length of the - optional study data, each written as four bytes in big-endian order - (most significant byte first). If there is no study data (either the + The data that is written is binary. The first eight bytes are the + length of the compiled pattern data followed by the length of the + optional study data, each written as four bytes in big-endian order + (most significant byte first). If there is no study data (either the pattern was not studied, or studying did not return any data), the sec- - ond length is zero. The lengths are followed by an exact copy of the + ond length is zero. The lengths are followed by an exact copy of the compiled pattern. If there is additional study data, this follows imme- - diately after the compiled pattern. After writing the file, pcretest + diately after the compiled pattern. After writing the file, pcretest expects to read a new pattern. A saved pattern can be reloaded into pcretest by specifing < and a file - name instead of a pattern. The name of the file must not contain a < - character, as otherwise pcretest will interpret the line as a pattern + name instead of a pattern. The name of the file must not contain a < + character, as otherwise pcretest will interpret the line as a pattern delimited by < characters. For example: re> </some/file Compiled regex loaded from /some/file No study data - When the pattern has been loaded, pcretest proceeds to read data lines + When the pattern has been loaded, pcretest proceeds to read data lines in the usual way. - You can copy a file written by pcretest to a different host and reload - it there, even if the new host has opposite endianness to the one on - which the pattern was compiled. For example, you can compile on an i86 + You can copy a file written by pcretest to a different host and reload + it there, even if the new host has opposite endianness to the one on + which the pattern was compiled. For example, you can compile on an i86 machine and run on a SPARC machine. - File names for saving and reloading can be absolute or relative, but - note that the shell facility of expanding a file name that starts with + File names for saving and reloading can be absolute or relative, but + note that the shell facility of expanding a file name that starts with a tilde (~) is not available. - The ability to save and reload files in pcretest is intended for test- - ing and experimentation. It is not intended for production use because - only a single pattern can be written to a file. Furthermore, there is - no facility for supplying custom character tables for use with a - reloaded pattern. If the original pattern was compiled with custom - tables, an attempt to match a subject string using a reloaded pattern - is likely to cause pcretest to crash. Finally, if you attempt to load + The ability to save and reload files in pcretest is intended for test- + ing and experimentation. It is not intended for production use because + only a single pattern can be written to a file. Furthermore, there is + no facility for supplying custom character tables for use with a + reloaded pattern. If the original pattern was compiled with custom + tables, an attempt to match a subject string using a reloaded pattern + is likely to cause pcretest to crash. Finally, if you attempt to load a file that is not in the correct format, the result is undefined. +SEE ALSO + + pcre(3), pcreapi(3), pcrecallout(3), pcrematching(3), pcrepartial(d), + pcrepattern(3), pcreprecompile(3). + + AUTHOR Philip Hazel - University Computing Service, - Cambridge CB2 3QG, England. + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION -Last updated: 29 June 2006 -Copyright (c) 1997-2006 University of Cambridge. + Last updated: 10 March 2009 + Copyright (c) 1997-2009 University of Cambridge. Modified: freeswitch/trunk/libs/pcre/libpcre.pc.in ============================================================================== --- freeswitch/trunk/libs/pcre/libpcre.pc.in (original) +++ freeswitch/trunk/libs/pcre/libpcre.pc.in Mon Jun 8 18:51:30 2009 @@ -7,6 +7,6 @@ Name: libpcre Description: PCRE - Perl compatible regular expressions C library -Version: @PCRE_VERSION@ +Version: @PACKAGE_VERSION@ Libs: -L${libdir} -lpcre Cflags: -I${includedir} Added: freeswitch/trunk/libs/pcre/libpcrecpp.pc.in ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/libpcrecpp.pc.in Mon Jun 8 18:51:30 2009 @@ -0,0 +1,12 @@ +# Package Information for pkg-config + +prefix=@prefix@ +exec_prefix=@exec_prefix@ +libdir=@libdir@ +includedir=@includedir@ + +Name: libpcrecpp +Description: PCRECPP - C++ wrapper for PCRE +Version: @PACKAGE_VERSION@ +Libs: -L${libdir} -lpcre -lpcrecpp +Cflags: -I${includedir} Modified: freeswitch/trunk/libs/pcre/makevp.bat ============================================================================== --- freeswitch/trunk/libs/pcre/makevp.bat (original) +++ freeswitch/trunk/libs/pcre/makevp.bat Mon Jun 8 18:51:30 2009 @@ -1,25 +1,66 @@ +:: AH 20-12-06 modified for new PCRE-7.0 and VP/BCC +:: PH 19-03-07 renamed !compile.txt and !linklib.txt as makevp-compile.txt and +:: makevp-linklib.txt +:: PH 26-03-07 re-renamed !compile.txt and !linklib.txt as makevp-c.txt and +:: makevp-l.txt +:: PH 29-03-07 hopefully the final rename to makevp_c and makevp_l +:: AH 27.08.08 updated for new PCRE-7.7 +:: required PCRE.H and CONFIG.H will be generated if not existing + @echo off +echo. +echo Compiling PCRE with BORLAND C++ for VIRTUAL PASCAL +echo. REM This file was contributed by Alexander Tokarev for building PCRE for use REM with Virtual Pascal. It has not been tested with the latest PCRE release. +REM This file has been modified and extended to compile with newer PCRE releases +REM by Stefan Weber (Angels Holocaust). + REM CHANGE THIS FOR YOUR BORLAND C++ COMPILER PATH +SET BORLAND=f:\bcc +REM location of the TASM binaries, if compiling with the -B BCC switch +SET TASM=f:\tasm + +SET PATH=%PATH%;%BORLAND%\bin;%TASM%\bin +SET PCRE_VER=77 +SET COMPILE_DEFAULTS=-DHAVE_CONFIG_H -DPCRE_STATIC -I%BORLAND%\include + +del pcre%PCRE_VER%.lib >nul 2>nul -SET BORLAND=c:\usr\apps\bcc55 +:: sh configure -sh configure +:: check for needed header files +if not exist pcre.h copy pcre.h.generic pcre.h +if not exist config.h copy config.h.generic config.h -bcc32 -DDFTABLES -DSTATIC -DVPCOMPAT -I%BORLAND%\include -L%BORLAND%\lib dftables.c +bcc32 -DDFTABLES %COMPILE_DEFAULTS% -L%BORLAND%\lib dftables.c +IF ERRORLEVEL 1 GOTO ERROR -dftables > chartables.c +:: dftables > chartables.c +dftables pcre_chartables.c -bcc32 -c -RT- -y- -v- -u- -P- -O2 -5 -DSTATIC -DVPCOMPAT -UDFTABLES -I%BORLAND%\include get.c maketables.c pcre.c study.c +REM compile and link the PCRE library into lib: option -B for ASM compile works too +bcc32 -a4 -c -RT- -y- -v- -u- -R- -Q- -X -d -fp -ff -P- -O2 -Oc -Ov -3 -w-8004 -w-8064 -w-8065 -w-8012 -UDFTABLES -DVPCOMPAT %COMPILE_DEFAULTS% @makevp_c.txt +IF ERRORLEVEL 1 GOTO ERROR -tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset -tlib pcre.lib +get.obj +maketables.obj +pcre.obj +study.obj +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj +tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset *memcmp *strlen +IF ERRORLEVEL 1 GOTO ERROR +tlib pcre%PCRE_VER%.lib @makevp_l.txt +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj +memcmp.obj +strlen.obj +IF ERRORLEVEL 1 GOTO ERROR -del *.obj *.exe *.tds *.bak >nul 2>nul +del *.obj *.tds *.bak >nul 2>nul echo --- echo Now the library should be complete. Please check all messages above. echo Don't care for warnings, it's OK. +goto END + +:ERROR +echo --- +echo Error while compiling PCRE. Aborting... +pause +goto END + +:END Added: freeswitch/trunk/libs/pcre/makevp_c.txt ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/makevp_c.txt Mon Jun 8 18:51:30 2009 @@ -0,0 +1,20 @@ +pcre_chartables.c +pcre_compile.c +pcre_config.c +pcre_dfa_exec.c +pcre_exec.c +pcre_fullinfo.c +pcre_get.c +pcre_globals.c +pcre_info.c +pcre_maketables.c +pcre_newline.c +pcre_ord2utf8.c +pcre_refcount.c +pcre_study.c +pcre_tables.c +pcre_try_flipped.c +pcre_ucd.c +pcre_valid_utf8.c +pcre_version.c +pcre_xclass.c Added: freeswitch/trunk/libs/pcre/makevp_l.txt ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/makevp_l.txt Mon Jun 8 18:51:30 2009 @@ -0,0 +1,20 @@ ++pcre_chartables.obj & ++pcre_compile.obj & ++pcre_config.obj & ++pcre_dfa_exec.obj & ++pcre_exec.obj & ++pcre_fullinfo.obj & ++pcre_get.obj & ++pcre_globals.obj & ++pcre_info.obj & ++pcre_maketables.obj & ++pcre_newline.obj & ++pcre_ord2utf8.obj & ++pcre_refcount.obj & ++pcre_study.obj & ++pcre_tables.obj & ++pcre_try_flipped.obj & ++pcre_ucd.obj & ++pcre_valid_utf8.obj & ++pcre_version.obj & ++pcre_xclass.obj Modified: freeswitch/trunk/libs/pcre/pcre-config.in ============================================================================== --- freeswitch/trunk/libs/pcre/pcre-config.in (original) +++ freeswitch/trunk/libs/pcre/pcre-config.in Mon Jun 8 18:51:30 2009 @@ -17,6 +17,9 @@ *SunOS*) libR=" -R@libdir@" ;; + *BSD*) + libR=" -Wl,-R@libdir@" + ;; esac while test $# -gt 0; do @@ -43,7 +46,7 @@ echo $exec_prefix ;; --version) - echo @PCRE_VERSION@ + echo @PACKAGE_VERSION@ ;; --cflags | --cflags-posix) if test @includedir@ != /usr/include ; then Modified: freeswitch/trunk/libs/pcre/pcre.h ============================================================================== --- freeswitch/trunk/libs/pcre/pcre.h (original) +++ freeswitch/trunk/libs/pcre/pcre.h Mon Jun 8 18:51:30 2009 @@ -5,7 +5,7 @@ /* This is the public header file for the PCRE library, to be #included by applications that call the PCRE functions. - Copyright (c) 1997-2005 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -41,44 +41,46 @@ /* The current PCRE version information. */ -/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because -they may be treated as octal constants. The PCRE_PRERELEASE feature is for -identifying release candidates. It might be defined as -RC2, for example. In -real releases, it should be defined empty. Do not change the alignment of these -statments. The code in ./configure greps out the version numbers by using "cut" -to get values from column 29 onwards. These are substituted into pcre-config -and libpcre.pc. The values are not put into configure.ac and substituted here -(which would simplify this issue) because that makes life harder for those who -cannot run ./configure. As it now stands, this file need not be edited in that -circumstance. */ - -#define PCRE_MAJOR 6 -#define PCRE_MINOR 7 -#define PCRE_PRERELEASE -#define PCRE_DATE 04-Jul-2006 - -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ - -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) +#define PCRE_MAJOR 7 +#define PCRE_MINOR 9 +#define PCRE_PRERELEASE +#define PCRE_DATE 2009-04-11 + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# ifndef PCRE_EXP_DECL +# define PCRE_EXP_DECL extern __declspec(dllimport) +# endif +# ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern __declspec(dllimport) # endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN __declspec(dllimport) # endif # endif #endif -/* Otherwise, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCRE_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCRE_EXP_DECL extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCRE_EXP_DECL extern +# endif +#endif + +#ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN # endif #endif @@ -93,7 +95,8 @@ extern "C" { #endif -/* Options */ +/* Options. Some are compile-time only, some are run-time only, and some are +both, so we keep them all distinct. */ #define PCRE_CASELESS 0x00000001 #define PCRE_MULTILINE 0x00000002 @@ -118,6 +121,13 @@ #define PCRE_NEWLINE_CR 0x00100000 #define PCRE_NEWLINE_LF 0x00200000 #define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 +#define PCRE_JAVASCRIPT_COMPAT 0x02000000 +#define PCRE_NO_START_OPTIMIZE 0x04000000 +#define PCRE_NO_START_OPTIMISE 0x04000000 /* Exec-time and get/set-time error codes */ @@ -125,7 +135,8 @@ #define PCRE_ERROR_NULL (-2) #define PCRE_ERROR_BADOPTION (-3) #define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_NODE (-5) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ #define PCRE_ERROR_NOMEMORY (-6) #define PCRE_ERROR_NOSUBSTRING (-7) #define PCRE_ERROR_MATCHLIMIT (-8) @@ -142,6 +153,8 @@ #define PCRE_ERROR_DFA_WSSIZE (-19) #define PCRE_ERROR_DFA_RECURSE (-20) #define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ +#define PCRE_ERROR_BADNEWLINE (-23) /* Request types for pcre_fullinfo() */ @@ -158,6 +171,9 @@ #define PCRE_INFO_NAMETABLE 9 #define PCRE_INFO_STUDYSIZE 10 #define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 +#define PCRE_INFO_HASCRORLF 14 /* Request types for pcre_config(). Do not re-arrange, in order to remain compatible. */ @@ -170,6 +186,7 @@ #define PCRE_CONFIG_STACKRECURSE 5 #define PCRE_CONFIG_UNICODE_PROPERTIES 6 #define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 /* Bit flags for the pcre_extra structure. Do not re-arrange or redefine these bits, just add new ones on the end, in order to remain compatible. */ @@ -236,52 +253,52 @@ have to take another form. */ #ifndef VPCOMPAT -PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); #else /* VPCOMPAT */ -PCRE_DATA_SCOPE void *pcre_malloc(size_t); -PCRE_DATA_SCOPE void pcre_free(void *); -PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); -PCRE_DATA_SCOPE void pcre_stack_free(void *); -PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); #endif /* VPCOMPAT */ /* Exported PCRE functions */ -PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE int pcre_config(int, void *); -PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, int *, int, const char *, char *, int); -PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, int); -PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, const char *, int, int, int, int *, int , int *, int); -PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, int, int, int, int *, int); -PCRE_DATA_SCOPE void pcre_free_substring(const char *); -PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); -PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, void *); -PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, int *, int, const char *, const char **); -PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); -PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, char **, char **); -PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, const char **); -PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, const char ***); -PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); -PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); -PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); -PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_DATA_SCOPE const char *pcre_version(void); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); #ifdef __cplusplus } /* extern "C" */ Added: freeswitch/trunk/libs/pcre/pcre.h.generic ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcre.h.generic Mon Jun 8 18:51:30 2009 @@ -0,0 +1,307 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. + + Copyright (c) 1997-2009 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef _PCRE_H +#define _PCRE_H + +/* The current PCRE version information. */ + +#define PCRE_MAJOR 7 +#define PCRE_MINOR 9 +#define PCRE_PRERELEASE +#define PCRE_DATE 2009-04-11 + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# ifndef PCRE_EXP_DECL +# define PCRE_EXP_DECL extern __declspec(dllimport) +# endif +# ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern __declspec(dllimport) +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN __declspec(dllimport) +# endif +# endif +#endif + +/* By default, we use the standard "extern" declarations. */ + +#ifndef PCRE_EXP_DECL +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +#endif + +#ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN +# endif +#endif + +/* Have to include stdlib.h in order to ensure that size_t is defined; +it is needed here for malloc. */ + +#include <stdlib.h> + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options. Some are compile-time only, some are run-time only, and some are +both, so we keep them all distinct. */ + +#define PCRE_CASELESS 0x00000001 +#define PCRE_MULTILINE 0x00000002 +#define PCRE_DOTALL 0x00000004 +#define PCRE_EXTENDED 0x00000008 +#define PCRE_ANCHORED 0x00000010 +#define PCRE_DOLLAR_ENDONLY 0x00000020 +#define PCRE_EXTRA 0x00000040 +#define PCRE_NOTBOL 0x00000080 +#define PCRE_NOTEOL 0x00000100 +#define PCRE_UNGREEDY 0x00000200 +#define PCRE_NOTEMPTY 0x00000400 +#define PCRE_UTF8 0x00000800 +#define PCRE_NO_AUTO_CAPTURE 0x00001000 +#define PCRE_NO_UTF8_CHECK 0x00002000 +#define PCRE_AUTO_CALLOUT 0x00004000 +#define PCRE_PARTIAL 0x00008000 +#define PCRE_DFA_SHORTEST 0x00010000 +#define PCRE_DFA_RESTART 0x00020000 +#define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 +#define PCRE_JAVASCRIPT_COMPAT 0x02000000 +#define PCRE_NO_START_OPTIMIZE 0x04000000 +#define PCRE_NO_START_OPTIMISE 0x04000000 + +/* Exec-time and get/set-time error codes */ + +#define PCRE_ERROR_NOMATCH (-1) +#define PCRE_ERROR_NULL (-2) +#define PCRE_ERROR_BADOPTION (-3) +#define PCRE_ERROR_BADMAGIC (-4) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ +#define PCRE_ERROR_NOMEMORY (-6) +#define PCRE_ERROR_NOSUBSTRING (-7) +#define PCRE_ERROR_MATCHLIMIT (-8) +#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ +#define PCRE_ERROR_BADUTF8 (-10) +#define PCRE_ERROR_BADUTF8_OFFSET (-11) +#define PCRE_ERROR_PARTIAL (-12) +#define PCRE_ERROR_BADPARTIAL (-13) +#define PCRE_ERROR_INTERNAL (-14) +#define PCRE_ERROR_BADCOUNT (-15) +#define PCRE_ERROR_DFA_UITEM (-16) +#define PCRE_ERROR_DFA_UCOND (-17) +#define PCRE_ERROR_DFA_UMLIMIT (-18) +#define PCRE_ERROR_DFA_WSSIZE (-19) +#define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ +#define PCRE_ERROR_BADNEWLINE (-23) + +/* Request types for pcre_fullinfo() */ + +#define PCRE_INFO_OPTIONS 0 +#define PCRE_INFO_SIZE 1 +#define PCRE_INFO_CAPTURECOUNT 2 +#define PCRE_INFO_BACKREFMAX 3 +#define PCRE_INFO_FIRSTBYTE 4 +#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ +#define PCRE_INFO_FIRSTTABLE 5 +#define PCRE_INFO_LASTLITERAL 6 +#define PCRE_INFO_NAMEENTRYSIZE 7 +#define PCRE_INFO_NAMECOUNT 8 +#define PCRE_INFO_NAMETABLE 9 +#define PCRE_INFO_STUDYSIZE 10 +#define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 +#define PCRE_INFO_HASCRORLF 14 + +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ + +#define PCRE_CONFIG_UTF8 0 +#define PCRE_CONFIG_NEWLINE 1 +#define PCRE_CONFIG_LINK_SIZE 2 +#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 +#define PCRE_CONFIG_MATCH_LIMIT 4 +#define PCRE_CONFIG_STACKRECURSE 5 +#define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 + +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ + +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 + +/* Types */ + +struct real_pcre; /* declaration; the definition is private */ +typedef struct real_pcre pcre; + +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + +/* The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. */ + +typedef struct pcre_extra { + unsigned long int flags; /* Bits for which fields are set */ + void *study_data; /* Opaque data from pcre_study() */ + unsigned long int match_limit; /* Maximum number of calls to match() */ + void *callout_data; /* Data passed back in callouts */ + const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ +} pcre_extra; + +/* The structure for passing out data via the pcre_callout_function. We use a +structure so that new fields can be added on the end in future versions, +without changing the API of the function, thereby allowing old clients to work +without modification. */ + +typedef struct pcre_callout_block { + int version; /* Identifies version of block */ + /* ------------------------ Version 0 ------------------------------- */ + int callout_number; /* Number compiled into pattern */ + int *offset_vector; /* The offset vector */ + PCRE_SPTR subject; /* The subject being matched */ + int subject_length; /* The length of the subject */ + int start_match; /* Offset to start of this match attempt */ + int current_position; /* Where we currently are in the subject */ + int capture_top; /* Max current capture */ + int capture_last; /* Most recently closed capture */ + void *callout_data; /* Data passed in with the call */ + /* ------------------- Added for Version 1 -------------------------- */ + int pattern_position; /* Offset to next item in the pattern */ + int next_item_length; /* Length of next item in the pattern */ + /* ------------------------------------------------------------------ */ +} pcre_callout_block; + +/* Indirection for store get and free functions. These can be set to +alternative malloc/free functions if required. Special ones are used in the +non-recursive case for "frames". There is also an optional callout function +that is triggered by the (?) regex item. For Virtual Pascal, these definitions +have to take another form. */ + +#ifndef VPCOMPAT +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); +#else /* VPCOMPAT */ +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); +#endif /* VPCOMPAT */ + +/* Exported PCRE functions */ + +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, + const unsigned char *); +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, + int *, const unsigned char *); +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, + int *, int, const char *, char *, int); +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, + int); +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, + const char *, int, int, int, int *, int , int *, int); +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, + int, int, int, int *, int); +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, + void *); +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, + int *, int, const char *, const char **); +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, + const char **); +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, + const char ***); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcre.h */ Added: freeswitch/trunk/libs/pcre/pcre.h.in ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcre.h.in Mon Jun 8 18:51:30 2009 @@ -0,0 +1,307 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. + + Copyright (c) 1997-2009 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef _PCRE_H +#define _PCRE_H + +/* The current PCRE version information. */ + +#define PCRE_MAJOR @PCRE_MAJOR@ +#define PCRE_MINOR @PCRE_MINOR@ +#define PCRE_PRERELEASE @PCRE_PRERELEASE@ +#define PCRE_DATE @PCRE_DATE@ + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# ifndef PCRE_EXP_DECL +# define PCRE_EXP_DECL extern __declspec(dllimport) +# endif +# ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern __declspec(dllimport) +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN __declspec(dllimport) +# endif +# endif +#endif + +/* By default, we use the standard "extern" declarations. */ + +#ifndef PCRE_EXP_DECL +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +#endif + +#ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN +# endif +#endif + +/* Have to include stdlib.h in order to ensure that size_t is defined; +it is needed here for malloc. */ + +#include <stdlib.h> + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options. Some are compile-time only, some are run-time only, and some are +both, so we keep them all distinct. */ + +#define PCRE_CASELESS 0x00000001 +#define PCRE_MULTILINE 0x00000002 +#define PCRE_DOTALL 0x00000004 +#define PCRE_EXTENDED 0x00000008 +#define PCRE_ANCHORED 0x00000010 +#define PCRE_DOLLAR_ENDONLY 0x00000020 +#define PCRE_EXTRA 0x00000040 +#define PCRE_NOTBOL 0x00000080 +#define PCRE_NOTEOL 0x00000100 +#define PCRE_UNGREEDY 0x00000200 +#define PCRE_NOTEMPTY 0x00000400 +#define PCRE_UTF8 0x00000800 +#define PCRE_NO_AUTO_CAPTURE 0x00001000 +#define PCRE_NO_UTF8_CHECK 0x00002000 +#define PCRE_AUTO_CALLOUT 0x00004000 +#define PCRE_PARTIAL 0x00008000 +#define PCRE_DFA_SHORTEST 0x00010000 +#define PCRE_DFA_RESTART 0x00020000 +#define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 +#define PCRE_JAVASCRIPT_COMPAT 0x02000000 +#define PCRE_NO_START_OPTIMIZE 0x04000000 +#define PCRE_NO_START_OPTIMISE 0x04000000 + +/* Exec-time and get/set-time error codes */ + +#define PCRE_ERROR_NOMATCH (-1) +#define PCRE_ERROR_NULL (-2) +#define PCRE_ERROR_BADOPTION (-3) +#define PCRE_ERROR_BADMAGIC (-4) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ +#define PCRE_ERROR_NOMEMORY (-6) +#define PCRE_ERROR_NOSUBSTRING (-7) +#define PCRE_ERROR_MATCHLIMIT (-8) +#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ +#define PCRE_ERROR_BADUTF8 (-10) +#define PCRE_ERROR_BADUTF8_OFFSET (-11) +#define PCRE_ERROR_PARTIAL (-12) +#define PCRE_ERROR_BADPARTIAL (-13) +#define PCRE_ERROR_INTERNAL (-14) +#define PCRE_ERROR_BADCOUNT (-15) +#define PCRE_ERROR_DFA_UITEM (-16) +#define PCRE_ERROR_DFA_UCOND (-17) +#define PCRE_ERROR_DFA_UMLIMIT (-18) +#define PCRE_ERROR_DFA_WSSIZE (-19) +#define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ +#define PCRE_ERROR_BADNEWLINE (-23) + +/* Request types for pcre_fullinfo() */ + +#define PCRE_INFO_OPTIONS 0 +#define PCRE_INFO_SIZE 1 +#define PCRE_INFO_CAPTURECOUNT 2 +#define PCRE_INFO_BACKREFMAX 3 +#define PCRE_INFO_FIRSTBYTE 4 +#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ +#define PCRE_INFO_FIRSTTABLE 5 +#define PCRE_INFO_LASTLITERAL 6 +#define PCRE_INFO_NAMEENTRYSIZE 7 +#define PCRE_INFO_NAMECOUNT 8 +#define PCRE_INFO_NAMETABLE 9 +#define PCRE_INFO_STUDYSIZE 10 +#define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 +#define PCRE_INFO_HASCRORLF 14 + +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ + +#define PCRE_CONFIG_UTF8 0 +#define PCRE_CONFIG_NEWLINE 1 +#define PCRE_CONFIG_LINK_SIZE 2 +#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 +#define PCRE_CONFIG_MATCH_LIMIT 4 +#define PCRE_CONFIG_STACKRECURSE 5 +#define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 + +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ + +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 + +/* Types */ + +struct real_pcre; /* declaration; the definition is private */ +typedef struct real_pcre pcre; + +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + +/* The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. */ + +typedef struct pcre_extra { + unsigned long int flags; /* Bits for which fields are set */ + void *study_data; /* Opaque data from pcre_study() */ + unsigned long int match_limit; /* Maximum number of calls to match() */ + void *callout_data; /* Data passed back in callouts */ + const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ +} pcre_extra; + +/* The structure for passing out data via the pcre_callout_function. We use a +structure so that new fields can be added on the end in future versions, +without changing the API of the function, thereby allowing old clients to work +without modification. */ + +typedef struct pcre_callout_block { + int version; /* Identifies version of block */ + /* ------------------------ Version 0 ------------------------------- */ + int callout_number; /* Number compiled into pattern */ + int *offset_vector; /* The offset vector */ + PCRE_SPTR subject; /* The subject being matched */ + int subject_length; /* The length of the subject */ + int start_match; /* Offset to start of this match attempt */ + int current_position; /* Where we currently are in the subject */ + int capture_top; /* Max current capture */ + int capture_last; /* Most recently closed capture */ + void *callout_data; /* Data passed in with the call */ + /* ------------------- Added for Version 1 -------------------------- */ + int pattern_position; /* Offset to next item in the pattern */ + int next_item_length; /* Length of next item in the pattern */ + /* ------------------------------------------------------------------ */ +} pcre_callout_block; + +/* Indirection for store get and free functions. These can be set to +alternative malloc/free functions if required. Special ones are used in the +non-recursive case for "frames". There is also an optional callout function +that is triggered by the (?) regex item. For Virtual Pascal, these definitions +have to take another form. */ + +#ifndef VPCOMPAT +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); +#else /* VPCOMPAT */ +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); +#endif /* VPCOMPAT */ + +/* Exported PCRE functions */ + +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, + const unsigned char *); +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, + int *, const unsigned char *); +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, + int *, int, const char *, char *, int); +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, + int); +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, + const char *, int, int, int, int *, int , int *, int); +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, + int, int, int, int *, int); +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, + void *); +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, + int *, int, const char *, const char **); +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, + const char **); +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, + const char ***); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcre.h */ Added: freeswitch/trunk/libs/pcre/pcre_chartables.c.dist ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcre_chartables.c.dist Mon Jun 8 18:51:30 2009 @@ -0,0 +1,198 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This file contains character tables that are used when no external tables +are passed to PCRE by the application that calls it. The tables are used only +for characters whose code values are less than 256. + +This is a default version of the tables that assumes ASCII encoding. A program +called dftables (which is distributed with PCRE) can be used to build +alternative versions of this file. This is necessary if you are running in an +EBCDIC environment, or if you want to default to a different encoding, for +example ISO-8859-1. When dftables is run, it creates these tables in the +current locale. If PCRE is configured with --enable-rebuild-chartables, this +happens automatically. + +The following #includes are present because without the gcc 4.x may remove the +array definition from the final binary if PCRE is built into a static library +and dead code stripping is activated. This leads to link errors. Pulling in the +header ensures that the array gets flagged as "someone outside this compilation +unit might reference this" and so it will always be supplied to the linker. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +const unsigned char _pcre_default_tables[] = { + +/* This table is a lower casing table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table is a case flipping table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 65, 66, 67, 68, 69, 70, 71, + 72, 73, 74, 75, 76, 77, 78, 79, + 80, 81, 82, 83, 84, 85, 86, 87, + 88, 89, 90,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table contains bit maps for various character classes. Each map is 32 +bytes long and the bits run from the least significant end of each byte. The +classes that have their own maps are: space, xdigit, digit, upper, lower, word, +graph, print, punct, and cntrl. Other classes are built from combinations. */ + + 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, + 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + +/* This table identifies various classes of character by individual bits: + 0x01 white space character + 0x02 letter + 0x04 decimal digit + 0x08 hexadecimal digit + 0x10 alphanumeric or '_' + 0x80 regular expression metacharacter or binary zero +*/ + + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ + 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +/* End of pcre_chartables.c */ Modified: freeswitch/trunk/libs/pcre/pcre_compile.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_compile.c (original) +++ freeswitch/trunk/libs/pcre/pcre_compile.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,7 +42,14 @@ supporting internal functions that are not used by other modules. */ -#define NLBLOCK cd /* The block containing newline information */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK cd /* Block containing newline information */ +#define PSSTART start_pattern /* Field containing processed string start */ +#define PSEND end_pattern /* Field containing processed string end */ + #include "pcre_internal.h" @@ -54,18 +61,35 @@ #endif +/* Macro for setting individual bits in class bitmaps. */ + +#define SETBIT(a,b) a[b/8] |= (1 << (b%8)) + +/* Maximum length value to check against when making sure that the integer that +holds the compiled pattern length does not overflow. We make it a bit less than +INT_MAX to allow for adding in group terminating bytes, so that we don't have +to check them every time. */ + +#define OFLOW_MAX (INT_MAX - 20) + /************************************************* * Code parameters and static tables * *************************************************/ -/* Maximum number of items on the nested bracket stacks at compile time. This -applies to the nesting of all kinds of parentheses. It does not limit -un-nested, non-capturing parentheses. This number can be made bigger if -necessary - it is used to dimension one int and one unsigned char vector at -compile time. */ +/* This value specifies the size of stack workspace that is used during the +first pre-compile phase that determines how much memory is required. The regex +is partly compiled into this space, but the compiled parts are discarded as +soon as they can be, so that hopefully there will never be an overrun. The code +does, however, check for an overrun. The largest amount I've seen used is 218, +so this number is very generous. + +The same workspace is used during the second, actual compile phase for +remembering forward references to groups so that they can be filled in at the +end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE +is 4 there is plenty of room. */ -#define BRASTACK_SIZE 200 +#define COMPILE_WORK_SIZE (4096) /* Table for handling escaped characters in the range '0'-'z'. Positive returns @@ -73,21 +97,56 @@ on. Zero means further processing is needed (for things like \x), or the escape is invalid. */ -#if !EBCDIC /* This is the "normal" table for ASCII systems */ +#ifndef EBCDIC + +/* This is the "normal" table for ASCII systems or for EBCDIC systems running +in UTF-8 mode. */ + static const short int escapes[] = { - 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ - 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ - '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ - 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ --ESC_P, -ESC_Q, 0, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ --ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ - '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ - 0, 0, 0, 0, 0, 0, ESC_n, 0, /* h - o */ --ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */ - 0, 0, -ESC_z /* x - z */ + 0, 0, + 0, 0, + 0, 0, + 0, 0, + 0, 0, + CHAR_COLON, CHAR_SEMICOLON, + CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, + CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK, + CHAR_COMMERCIAL_AT, -ESC_A, + -ESC_B, -ESC_C, + -ESC_D, -ESC_E, + 0, -ESC_G, + -ESC_H, 0, + 0, -ESC_K, + 0, 0, + 0, 0, + -ESC_P, -ESC_Q, + -ESC_R, -ESC_S, + 0, 0, + -ESC_V, -ESC_W, + -ESC_X, 0, + -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, + CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, + CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, + CHAR_GRAVE_ACCENT, 7, + -ESC_b, 0, + -ESC_d, ESC_e, + ESC_f, 0, + -ESC_h, 0, + 0, -ESC_k, + 0, 0, + ESC_n, 0, + -ESC_p, 0, + ESC_r, -ESC_s, + ESC_tee, 0, + -ESC_v, -ESC_w, + 0, 0, + -ESC_z }; -#else /* This is the "abnormal" table for EBCDIC systems */ +#else + +/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */ + static const short int escapes[] = { /* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', /* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, @@ -97,18 +156,18 @@ /* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, /* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', /* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */ 0, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, 0, 'l', 0, ESC_n, 0, -ESC_p, +/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, +/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, /* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -ESC_w, 0, +/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, /* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, /* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', /* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P, -/* D8 */-ESC_Q, 0, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -ESC_W, -ESC_X, +/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, +/* D0 */ '}', 0, -ESC_K, 0, 0, 0, 0, -ESC_P, +/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, +/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, /* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, /* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 @@ -116,14 +175,50 @@ #endif -/* Tables of names of POSIX character classes and their lengths. The list is -terminated by a zero length entry. The first three must be alpha, lower, upper, -as this is assumed for handling case independence. */ - -static const char *const posix_names[] = { - "alpha", "lower", "upper", - "alnum", "ascii", "blank", "cntrl", "digit", "graph", - "print", "punct", "space", "word", "xdigit" }; +/* Table of special "verbs" like (*PRUNE). This is a short table, so it is +searched linearly. Put all the names into a single string, in order to reduce +the number of relocations when a shared library is dynamically linked. The +string is built from string macros so that it works in UTF-8 mode on EBCDIC +platforms. */ + +typedef struct verbitem { + int len; + int op; +} verbitem; + +static const char verbnames[] = + STRING_ACCEPT0 + STRING_COMMIT0 + STRING_F0 + STRING_FAIL0 + STRING_PRUNE0 + STRING_SKIP0 + STRING_THEN; + +static const verbitem verbs[] = { + { 6, OP_ACCEPT }, + { 6, OP_COMMIT }, + { 1, OP_FAIL }, + { 4, OP_FAIL }, + { 5, OP_PRUNE }, + { 4, OP_SKIP }, + { 4, OP_THEN } +}; + +static const int verbcount = sizeof(verbs)/sizeof(verbitem); + + +/* Tables of names of POSIX character classes and their lengths. The names are +now all in a single string, to reduce the number of relocations when a shared +library is dynamically loaded. The list of lengths is terminated by a zero +length entry. The first three must be alpha, lower, upper, as this is assumed +for handling case independence. */ + +static const char posix_names[] = + STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0 + STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0 + STRING_graph0 STRING_print0 STRING_punct0 STRING_space0 + STRING_word0 STRING_xdigit; static const uschar posix_name_lengths[] = { 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; @@ -156,73 +251,97 @@ }; -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. */ +#define STRING(a) # a +#define XSTRING(s) STRING(s) -static const char *error_texts[] = { - "no error", - "\\ at end of pattern", - "\\c at end of pattern", - "unrecognized character follows \\", - "numbers out of order in {} quantifier", +/* The texts of compile-time error messages. These are "char *" because they +are passed to the outside world. Do not ever re-use any error number, because +they are documented. Always add a new error instead. Messages marked DEAD below +are no longer used. This used to be a table of strings, but in order to reduce +the number of relocations needed when a shared library is loaded dynamically, +it is now one long string. We cannot use a table of offsets, because the +lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we +simply count through to the one we want - this isn't a performance issue +because these strings are used only when there is a compilation error. */ + +static const char error_texts[] = + "no error\0" + "\\ at end of pattern\0" + "\\c at end of pattern\0" + "unrecognized character follows \\\0" + "numbers out of order in {} quantifier\0" /* 5 */ - "number too big in {} quantifier", - "missing terminating ] for character class", - "invalid escape sequence in character class", - "range out of order in character class", - "nothing to repeat", + "number too big in {} quantifier\0" + "missing terminating ] for character class\0" + "invalid escape sequence in character class\0" + "range out of order in character class\0" + "nothing to repeat\0" /* 10 */ - "operand of unlimited repeat could match the empty string", - "internal error: unexpected repeat", - "unrecognized character after (?", - "POSIX named classes are supported only within a class", - "missing )", + "operand of unlimited repeat could match the empty string\0" /** DEAD **/ + "internal error: unexpected repeat\0" + "unrecognized character after (? or (?-\0" + "POSIX named classes are supported only within a class\0" + "missing )\0" /* 15 */ - "reference to non-existent subpattern", - "erroffset passed as NULL", - "unknown option bit(s) set", - "missing ) after comment", - "parentheses nested too deeply", + "reference to non-existent subpattern\0" + "erroffset passed as NULL\0" + "unknown option bit(s) set\0" + "missing ) after comment\0" + "parentheses nested too deeply\0" /** DEAD **/ /* 20 */ - "regular expression too large", - "failed to get memory", - "unmatched parentheses", - "internal error: code overflow", - "unrecognized character after (?<", + "regular expression is too large\0" + "failed to get memory\0" + "unmatched parentheses\0" + "internal error: code overflow\0" + "unrecognized character after (?<\0" /* 25 */ - "lookbehind assertion is not fixed length", - "malformed number or name after (?(", - "conditional group contains more than two branches", - "assertion expected after (?(", - "(?R or (?digits must be followed by )", + "lookbehind assertion is not fixed length\0" + "malformed number or name after (?(\0" + "conditional group contains more than two branches\0" + "assertion expected after (?(\0" + "(?R or (?[+-]digits must be followed by )\0" /* 30 */ - "unknown POSIX class name", - "POSIX collating elements are not supported", - "this version of PCRE is not compiled with PCRE_UTF8 support", - "spare error", - "character value in \\x{...} sequence is too large", + "unknown POSIX class name\0" + "POSIX collating elements are not supported\0" + "this version of PCRE is not compiled with PCRE_UTF8 support\0" + "spare error\0" /** DEAD **/ + "character value in \\x{...} sequence is too large\0" /* 35 */ - "invalid condition (?(0)", - "\\C not allowed in lookbehind assertion", - "PCRE does not support \\L, \\l, \\N, \\U, or \\u", - "number after (?C is > 255", - "closing ) for (?C expected", + "invalid condition (?(0)\0" + "\\C not allowed in lookbehind assertion\0" + "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0" + "number after (?C is > 255\0" + "closing ) for (?C expected\0" /* 40 */ - "recursive call could loop indefinitely", - "unrecognized character after (?P", - "syntax error after (?P", - "two named subpatterns have the same name", - "invalid UTF-8 string", + "recursive call could loop indefinitely\0" + "unrecognized character after (?P\0" + "syntax error in subpattern name (missing terminator)\0" + "two named subpatterns have the same name\0" + "invalid UTF-8 string\0" /* 45 */ - "support for \\P, \\p, and \\X has not been compiled", - "malformed \\P or \\p sequence", - "unknown property name after \\P or \\p", - "subpattern name is too long (maximum 32 characters)", - "too many named subpatterns (maximum 10,000)", + "support for \\P, \\p, and \\X has not been compiled\0" + "malformed \\P or \\p sequence\0" + "unknown property name after \\P or \\p\0" + "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" + "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" /* 50 */ - "repeated subpattern is too long", - "octal value is greater than \\377 (not in UTF-8 mode)" -}; + "repeated subpattern is too long\0" /** DEAD **/ + "octal value is greater than \\377 (not in UTF-8 mode)\0" + "internal error: overran compiling workspace\0" + "internal error: previously-checked referenced subpattern not found\0" + "DEFINE group contains more than one branch\0" + /* 55 */ + "repeating a DEFINE group is not allowed\0" + "inconsistent NEWLINE options\0" + "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0" + "a numbered reference must not be zero\0" + "(*VERB) with an argument is not supported\0" + /* 60 */ + "(*VERB) not recognized\0" + "number is too big\0" + "subpattern name expected\0" + "digit expected after (?+\0" + "] is an invalid data character in JavaScript compatibility mode"; /* Table to identify digits and hex digits. This is used when compiling @@ -241,7 +360,11 @@ Then we can use ctype_digit and ctype_xdigit in the code. */ -#if !EBCDIC /* This is the "normal" case, for ASCII systems */ +#ifndef EBCDIC + +/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in +UTF-8 mode. */ + static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ @@ -277,7 +400,10 @@ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ -#else /* This is the "abnormal" case, for EBCDIC systems */ +#else + +/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */ + static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ @@ -291,7 +417,7 @@ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- � */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ @@ -325,7 +451,7 @@ 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- � */ + 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ @@ -352,9 +478,31 @@ /* Definition to allow mutual recursion */ static BOOL - compile_regex(int, int, int *, uschar **, const uschar **, int *, BOOL, int, - int *, int *, branch_chain *, compile_data *); + compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int, + int *, int *, branch_chain *, compile_data *, int *); + + + +/************************************************* +* Find an error text * +*************************************************/ + +/* The error texts are now all in one long string, to save on relocations. As +some of the text is of unknown length, we can't use a table of offsets. +Instead, just count through the strings. This is not a performance issue +because it happens only when there has been a compilation error. + +Argument: the error number +Returns: pointer to the error string +*/ +static const char * +find_error_text(int n) +{ +const char *s = error_texts; +for (; n > 0; n--) while (*s++ != 0) {}; +return s; +} /************************************************* @@ -363,9 +511,11 @@ /* This function is called when a \ has been encountered. It either returns a positive value for a simple escape such as \n, or a negative value which -encodes one of the more complicated things such as \d. When UTF-8 is enabled, -a positive value greater than 255 may be returned. On entry, ptr is pointing at -the \. On exit, it is on the final character of the escape sequence. +encodes one of the more complicated things such as \d. A backreference to group +n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When +UTF-8 is enabled, a positive value greater than 255 may be returned. On entry, +ptr is pointing at the \. On exit, it is on the final character of the escape +sequence. Arguments: ptrptr points to the pattern position pointer @@ -376,7 +526,7 @@ Returns: zero or positive => a data character negative => a special escape sequence - on error, errorptr is set + on error, errorcodeptr is set */ static int @@ -394,16 +544,16 @@ if (c == 0) *errorcodeptr = ERR1; -/* Non-alphamerics are literals. For digits or letters, do an initial lookup in -a table. A non-zero result is something that can be returned immediately. +/* Non-alphanumerics are literals. For digits or letters, do an initial lookup +in a table. A non-zero result is something that can be returned immediately. Otherwise further processing may be required. */ -#if !EBCDIC /* ASCII coding */ -else if (c < '0' || c > 'z') {} /* Not alphameric */ -else if ((i = escapes[c - '0']) != 0) c = i; +#ifndef EBCDIC /* ASCII/UTF-8 coding */ +else if (c < CHAR_0 || c > CHAR_z) {} /* Not alphanumeric */ +else if ((i = escapes[c - CHAR_0]) != 0) c = i; -#else /* EBCDIC coding */ -else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ +#else /* EBCDIC coding */ +else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphanumeric */ else if ((i = escapes[c - 0x48]) != 0) c = i; #endif @@ -412,19 +562,103 @@ else { const uschar *oldptr; + BOOL braced, negated; + switch (c) { /* A number of Perl escapes are not handled by PCRE. We give an explicit error. */ - case 'l': - case 'L': - case 'N': - case 'u': - case 'U': + case CHAR_l: + case CHAR_L: + case CHAR_N: + case CHAR_u: + case CHAR_U: *errorcodeptr = ERR37; break; + /* \g must be followed by one of a number of specific things: + + (1) A number, either plain or braced. If positive, it is an absolute + backreference. If negative, it is a relative backreference. This is a Perl + 5.10 feature. + + (2) Perl 5.10 also supports \g{name} as a reference to a named group. This + is part of Perl's movement towards a unified syntax for back references. As + this is synonymous with \k{name}, we fudge it up by pretending it really + was \k. + + (3) For Oniguruma compatibility we also support \g followed by a name or a + number either in angle brackets or in single quotes. However, these are + (possibly recursive) subroutine calls, _not_ backreferences. Just return + the -ESC_g code (cf \k). */ + + case CHAR_g: + if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE) + { + c = -ESC_g; + break; + } + + /* Handle the Perl-compatible cases */ + + if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) + { + const uschar *p; + for (p = ptr+2; *p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET; p++) + if (*p != CHAR_MINUS && (digitab[*p] & ctype_digit) == 0) break; + if (*p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET) + { + c = -ESC_k; + break; + } + braced = TRUE; + ptr++; + } + else braced = FALSE; + + if (ptr[1] == CHAR_MINUS) + { + negated = TRUE; + ptr++; + } + else negated = FALSE; + + c = 0; + while ((digitab[ptr[1]] & ctype_digit) != 0) + c = c * 10 + *(++ptr) - CHAR_0; + + if (c < 0) /* Integer overflow */ + { + *errorcodeptr = ERR61; + break; + } + + if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET) + { + *errorcodeptr = ERR57; + break; + } + + if (c == 0) + { + *errorcodeptr = ERR58; + break; + } + + if (negated) + { + if (c > bracount) + { + *errorcodeptr = ERR15; + break; + } + c = bracount - (c - 1); + } + + c = -(ESC_REF + c); + break; + /* The handling of escape sequences consisting of a string of digits starting with one that is not zero is not straightforward. By experiment, the way Perl works seems to be as follows: @@ -437,15 +671,20 @@ value is greater than 377, the least significant 8 bits are taken. Inside a character class, \ followed by a digit is always an octal number. */ - case '1': case '2': case '3': case '4': case '5': - case '6': case '7': case '8': case '9': + case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5: + case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: if (!isclass) { oldptr = ptr; - c -= '0'; + c -= CHAR_0; while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - '0'; + c = c * 10 + *(++ptr) - CHAR_0; + if (c < 0) /* Integer overflow */ + { + *errorcodeptr = ERR61; + break; + } if (c < 10 || c <= bracount) { c = -(ESC_REF + c); @@ -458,7 +697,7 @@ generates a binary zero byte and treats the digit as a following literal. Thus we have to pull back the pointer by one. */ - if ((c = *ptr) >= '8') + if ((c = *ptr) >= CHAR_8) { ptr--; c = 0; @@ -471,10 +710,10 @@ to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more than 3 octal digits. */ - case '0': - c -= '0'; - while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7') - c = c * 8 + *(++ptr) - '0'; + case CHAR_0: + c -= CHAR_0; + while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) + c = c * 8 + *(++ptr) - CHAR_0; if (!utf8 && c > 255) *errorcodeptr = ERR51; break; @@ -482,8 +721,8 @@ than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is treated as a data character. */ - case 'x': - if (ptr[1] == '{') + case CHAR_x: + if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) { const uschar *pt = ptr + 2; int count = 0; @@ -492,19 +731,19 @@ while ((digitab[*pt] & ctype_xdigit) != 0) { register int cc = *pt++; - if (c == 0 && cc == '0') continue; /* Leading zeroes */ + if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ count++; -#if !EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); #endif } - if (*pt == '}') + if (*pt == CHAR_RIGHT_CURLY_BRACKET) { if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34; ptr = pt; @@ -520,46 +759,44 @@ c = 0; while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0) { - int cc; /* Some compilers don't like ++ */ - cc = *(++ptr); /* in initializers */ -#if !EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc <= 'z') cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); + int cc; /* Some compilers don't like */ + cc = *(++ptr); /* ++ in initializers */ +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); #endif } break; - /* Other special escapes not starting with a digit are straightforward */ + /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. + This coding is ASCII-specific, but then the whole concept of \cx is + ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ - case 'c': + case CHAR_c: c = *(++ptr); if (c == 0) { *errorcodeptr = ERR2; - return 0; + break; } - /* A letter is upper-cased; then the 0x40 bit is flipped. This coding - is ASCII-specific, but then the whole concept of \cx is ASCII-specific. - (However, an EBCDIC equivalent has now been added.) */ - -#if !EBCDIC /* ASCII coding */ - if (c >= 'a' && c <= 'z') c -= 32; +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (c >= CHAR_a && c <= CHAR_z) c -= 32; c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= 'a' && c <= 'z') c += 64; +#else /* EBCDIC coding */ + if (c >= CHAR_a && c <= CHAR_z) c += 64; c ^= 0xC0; #endif break; /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphameric following \ is an error if PCRE_EXTRA was set; otherwise, - for Perl compatibility, it is a literal. This code looks a bit odd, but - there used to be some cases other than the default, and there may be again - in future, so I haven't "optimized" it. */ + other alphanumeric following \ is an error if PCRE_EXTRA was set; + otherwise, for Perl compatibility, it is a literal. This code looks a bit + odd, but there used to be some cases other than the default, and there may + be again in future, so I haven't "optimized" it. */ default: if ((options & PCRE_EXTRA) != 0) switch(c) @@ -612,21 +849,21 @@ /* \P or \p can be followed by a name in {}, optionally preceded by ^ for negation. */ -if (c == '{') +if (c == CHAR_LEFT_CURLY_BRACKET) { - if (ptr[1] == '^') + if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT) { *negptr = TRUE; ptr++; } - for (i = 0; i < sizeof(name) - 1; i++) + for (i = 0; i < (int)sizeof(name) - 1; i++) { c = *(++ptr); if (c == 0) goto ERROR_RETURN; - if (c == '}') break; + if (c == CHAR_RIGHT_CURLY_BRACKET) break; name[i] = c; } - if (c !='}') goto ERROR_RETURN; + if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN; name[i] = 0; } @@ -648,7 +885,7 @@ while (bot < top) { i = (bot + top) >> 1; - c = strcmp(name, _pcre_utt[i].name); + c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset); if (c == 0) { *dptr = _pcre_utt[i].value; @@ -691,15 +928,15 @@ { if ((digitab[*p++] & ctype_digit) == 0) return FALSE; while ((digitab[*p] & ctype_digit) != 0) p++; -if (*p == '}') return TRUE; +if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; -if (*p++ != ',') return FALSE; -if (*p == '}') return TRUE; +if (*p++ != CHAR_COMMA) return FALSE; +if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; if ((digitab[*p++] & ctype_digit) == 0) return FALSE; while ((digitab[*p] & ctype_digit) != 0) p++; -return (*p == '}'); +return (*p == CHAR_RIGHT_CURLY_BRACKET); } @@ -732,7 +969,7 @@ /* Read the minimum value and do a paranoid check: a negative value indicates an integer overflow. */ -while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0'; +while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - CHAR_0; if (min < 0 || min > 65535) { *errorcodeptr = ERR5; @@ -742,12 +979,12 @@ /* Read the maximum value if there is one, and again do a paranoid on its size. Also, max must not be less than min. */ -if (*p == '}') max = min; else +if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else { - if (*(++p) != '}') + if (*(++p) != CHAR_RIGHT_CURLY_BRACKET) { max = 0; - while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0'; + while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - CHAR_0; if (max < 0 || max > 65535) { *errorcodeptr = ERR5; @@ -772,47 +1009,260 @@ /************************************************* -* Find forward referenced named subpattern * +* Subroutine for finding forward reference * *************************************************/ -/* This function scans along a pattern looking for capturing subpatterns, and -counting them. If it finds a named pattern that matches the name it is given, -it returns its number. This is used for forward references to named -subpatterns. We know that if (?P< is encountered, the name will be terminated -by '>' because that is checked in the first pass. +/* This recursive function is called only from find_parens() below. The +top-level call starts at the beginning of the pattern. All other calls must +start at a parenthesis. It scans along a pattern's text looking for capturing +subpatterns, and counting them. If it finds a named pattern that matches the +name it is given, it returns its number. Alternatively, if the name is NULL, it +returns when it reaches a given numbered subpattern. We know that if (?P< is +encountered, the name will be terminated by '>' because that is checked in the +first pass. Recursion is used to keep track of subpatterns that reset the +capturing group numbers - the (?| feature. Arguments: - pointer current position in the pattern - count current count of capturing parens - name name to seek - namelen name length + ptrptr address of the current character pointer (updated) + cd compile background data + name name to seek, or NULL if seeking a numbered subpattern + lorn name length, or subpattern number if name is NULL + xmode TRUE if we are in /x mode + count pointer to the current capturing subpattern number (updated) Returns: the number of the named subpattern, or -1 if not found */ static int -find_named_parens(const uschar *ptr, int count, const uschar *name, int namelen) +find_parens_sub(uschar **ptrptr, compile_data *cd, const uschar *name, int lorn, + BOOL xmode, int *count) { -const uschar *thisname; +uschar *ptr = *ptrptr; +int start_count = *count; +int hwm_count = start_count; +BOOL dup_parens = FALSE; + +/* If the first character is a parenthesis, check on the type of group we are +dealing with. The very first call may not start with a parenthesis. */ + +if (ptr[0] == CHAR_LEFT_PARENTHESIS) + { + if (ptr[1] == CHAR_QUESTION_MARK && + ptr[2] == CHAR_VERTICAL_LINE) + { + ptr += 3; + dup_parens = TRUE; + } + + /* Handle a normal, unnamed capturing parenthesis */ + + else if (ptr[1] != CHAR_QUESTION_MARK && ptr[1] != CHAR_ASTERISK) + { + *count += 1; + if (name == NULL && *count == lorn) return *count; + ptr++; + } + + /* Handle a condition. If it is an assertion, just carry on so that it + is processed as normal. If not, skip to the closing parenthesis of the + condition (there can't be any nested parens. */ + + else if (ptr[2] == CHAR_LEFT_PARENTHESIS) + { + ptr += 2; + if (ptr[1] != CHAR_QUESTION_MARK) + { + while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; + if (*ptr != 0) ptr++; + } + } + + /* We have either (? or (* and not a condition */ + + else + { + ptr += 2; + if (*ptr == CHAR_P) ptr++; /* Allow optional P */ + + /* We have to disambiguate (?<! and (?<= from (?<name> for named groups */ + + if ((*ptr == CHAR_LESS_THAN_SIGN && ptr[1] != CHAR_EXCLAMATION_MARK && + ptr[1] != CHAR_EQUALS_SIGN) || *ptr == CHAR_APOSTROPHE) + { + int term; + const uschar *thisname; + *count += 1; + if (name == NULL && *count == lorn) return *count; + term = *ptr++; + if (term == CHAR_LESS_THAN_SIGN) term = CHAR_GREATER_THAN_SIGN; + thisname = ptr; + while (*ptr != term) ptr++; + if (name != NULL && lorn == ptr - thisname && + strncmp((const char *)name, (const char *)thisname, lorn) == 0) + return *count; + } + } + } + +/* Past any initial parenthesis handling, scan for parentheses or vertical +bars. */ + for (; *ptr != 0; ptr++) { - if (*ptr == '\\' && ptr[1] != 0) { ptr++; continue; } - if (*ptr != '(') continue; - if (ptr[1] != '?') { count++; continue; } - if (ptr[2] == '(') { ptr += 2; continue; } - if (ptr[2] != 'P' || ptr[3] != '<') continue; - count++; - ptr += 4; - thisname = ptr; - while (*ptr != '>') ptr++; - if (namelen == ptr - thisname && strncmp(name, thisname, namelen) == 0) - return count; + /* Skip over backslashed characters and also entire \Q...\E */ + + if (*ptr == CHAR_BACKSLASH) + { + if (*(++ptr) == 0) goto FAIL_EXIT; + if (*ptr == CHAR_Q) for (;;) + { + while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {}; + if (*ptr == 0) goto FAIL_EXIT; + if (*(++ptr) == CHAR_E) break; + } + continue; + } + + /* Skip over character classes; this logic must be similar to the way they + are handled for real. If the first character is '^', skip it. Also, if the + first few characters (either before or after ^) are \Q\E or \E we skip them + too. This makes for compatibility with Perl. Note the use of STR macros to + encode "Q\\E" so that it works in UTF-8 on EBCDIC platforms. */ + + if (*ptr == CHAR_LEFT_SQUARE_BRACKET) + { + BOOL negate_class = FALSE; + for (;;) + { + int c = *(++ptr); + if (c == CHAR_BACKSLASH) + { + if (ptr[1] == CHAR_E) + ptr++; + else if (strncmp((const char *)ptr+1, + STR_Q STR_BACKSLASH STR_E, 3) == 0) + ptr += 3; + else + break; + } + else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) + negate_class = TRUE; + else break; + } + + /* If the next character is ']', it is a data character that must be + skipped, except in JavaScript compatibility mode. */ + + if (ptr[1] == CHAR_RIGHT_SQUARE_BRACKET && + (cd->external_options & PCRE_JAVASCRIPT_COMPAT) == 0) + ptr++; + + while (*(++ptr) != CHAR_RIGHT_SQUARE_BRACKET) + { + if (*ptr == 0) return -1; + if (*ptr == CHAR_BACKSLASH) + { + if (*(++ptr) == 0) goto FAIL_EXIT; + if (*ptr == CHAR_Q) for (;;) + { + while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {}; + if (*ptr == 0) goto FAIL_EXIT; + if (*(++ptr) == CHAR_E) break; + } + continue; + } + } + continue; + } + + /* Skip comments in /x mode */ + + if (xmode && *ptr == CHAR_NUMBER_SIGN) + { + while (*(++ptr) != 0 && *ptr != CHAR_NL) {}; + if (*ptr == 0) goto FAIL_EXIT; + continue; + } + + /* Check for the special metacharacters */ + + if (*ptr == CHAR_LEFT_PARENTHESIS) + { + int rc = find_parens_sub(&ptr, cd, name, lorn, xmode, count); + if (rc > 0) return rc; + if (*ptr == 0) goto FAIL_EXIT; + } + + else if (*ptr == CHAR_RIGHT_PARENTHESIS) + { + if (dup_parens && *count < hwm_count) *count = hwm_count; + *ptrptr = ptr; + return -1; + } + + else if (*ptr == CHAR_VERTICAL_LINE && dup_parens) + { + if (*count > hwm_count) hwm_count = *count; + *count = start_count; + } } + +FAIL_EXIT: +*ptrptr = ptr; return -1; } + +/************************************************* +* Find forward referenced subpattern * +*************************************************/ + +/* This function scans along a pattern's text looking for capturing +subpatterns, and counting them. If it finds a named pattern that matches the +name it is given, it returns its number. Alternatively, if the name is NULL, it +returns when it reaches a given numbered subpattern. This is used for forward +references to subpatterns. We used to be able to start this scan from the +current compiling point, using the current count value from cd->bracount, and +do it all in a single loop, but the addition of the possibility of duplicate +subpattern numbers means that we have to scan from the very start, in order to +take account of such duplicates, and to use a recursive function to keep track +of the different types of group. + +Arguments: + cd compile background data + name name to seek, or NULL if seeking a numbered subpattern + lorn name length, or subpattern number if name is NULL + xmode TRUE if we are in /x mode + +Returns: the number of the found subpattern, or -1 if not found +*/ + +static int +find_parens(compile_data *cd, const uschar *name, int lorn, BOOL xmode) +{ +uschar *ptr = (uschar *)cd->start_pattern; +int count = 0; +int rc; + +/* If the pattern does not start with an opening parenthesis, the first call +to find_parens_sub() will scan right to the end (if necessary). However, if it +does start with a parenthesis, find_parens_sub() will return when it hits the +matching closing parens. That is why we have to have a loop. */ + +for (;;) + { + rc = find_parens_sub(&ptr, cd, name, lorn, xmode, &count); + if (rc > 0 || *ptr++ == 0) break; + } + +return rc; +} + + + + /************************************************* * Find first significant op code * *************************************************/ @@ -862,7 +1312,8 @@ case OP_CALLOUT: case OP_CREF: - case OP_BRANUMBER: + case OP_RREF: + case OP_DEF: code += _pcre_OP_lengths[*code]; break; @@ -907,14 +1358,13 @@ { int d; register int op = *cc; - if (op >= OP_BRA) op = OP_BRA; - switch (op) { + case OP_CBRA: case OP_BRA: case OP_ONCE: case OP_COND: - d = find_fixedlength(cc, options); + d = find_fixedlength(cc + ((op == OP_CBRA)? 2:0), options); if (d < 0) return d; branchlength += d; do cc += GET(cc, 1); while (*cc == OP_ALT); @@ -949,8 +1399,9 @@ /* Skip over things that don't match chars */ case OP_REVERSE: - case OP_BRANUMBER: case OP_CREF: + case OP_RREF: + case OP_DEF: case OP_OPT: case OP_CALLOUT: case OP_SOD: @@ -995,6 +1446,7 @@ case OP_TYPEEXACT: branchlength += GET2(cc,1); + if (cc[3] == OP_PROP || cc[3] == OP_NOTPROP) cc += 2; cc += 4; break; @@ -1012,6 +1464,7 @@ case OP_NOT_WORDCHAR: case OP_WORDCHAR: case OP_ANY: + case OP_ALLANY: branchlength++; cc++; break; @@ -1094,25 +1547,52 @@ if (c == OP_XCLASS) code += GET(code, 1); - /* Handle bracketed group */ + /* Handle capturing bracket */ - else if (c > OP_BRA) + else if (c == OP_CBRA) { - int n = c - OP_BRA; - if (n > EXTRACT_BASIC_MAX) n = GET2(code, 2+LINK_SIZE); + int n = GET2(code, 1+LINK_SIZE); if (n == number) return (uschar *)code; - code += _pcre_OP_lengths[OP_BRA]; + code += _pcre_OP_lengths[c]; } - /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes - that are followed by a character may be followed by a multi-byte character. - The length in the table is a minimum, so we have to scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ + /* Otherwise, we can get the item's length from the table, except that for + repeated character types, we have to test for \p and \P, which have an extra + two bytes of parameters. */ else { + switch(c) + { + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSUPTO: + if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; + break; + } + + /* Add in the fixed length from the table */ + code += _pcre_OP_lengths[c]; + + /* In UTF-8 mode, opcodes that are followed by a character may be followed by + a multi-byte character. The length in the table is a minimum, so we have to + arrange to skip the extra bytes. */ + +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1120,15 +1600,22 @@ case OP_EXACT: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_QUERY: case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; + case OP_POSQUERY: + if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#else + (void)(utf8); /* Keep compiler happy by referencing function argument */ +#endif } } } @@ -1164,22 +1651,43 @@ if (c == OP_XCLASS) code += GET(code, 1); - /* All bracketed groups have the same length. */ + /* Otherwise, we can get the item's length from the table, except that for + repeated character types, we have to test for \p and \P, which have an extra + two bytes of parameters. */ - else if (c > OP_BRA) + else { - code += _pcre_OP_lengths[OP_BRA]; - } + switch(c) + { + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; - /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes - that are followed by a character may be followed by a multi-byte character. - The length in the table is a minimum, so we have to scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ + case OP_TYPEPOSUPTO: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; + break; + } + + /* Add in the fixed length from the table */ - else - { code += _pcre_OP_lengths[c]; + + /* In UTF-8 mode, opcodes that are followed by a character may be followed + by a multi-byte character. The length in the table is a minimum, so we have + to arrange to skip the extra bytes. */ + +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1187,15 +1695,22 @@ case OP_EXACT: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_QUERY: case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; + case OP_POSQUERY: + if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#else + (void)(utf8); /* Keep compiler happy by referencing function argument */ +#endif } } } @@ -1207,10 +1722,12 @@ *************************************************/ /* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called only from could_be_empty() -below. Note that first_significant_code() skips over assertions. If we hit an -unclosed bracket, we return "empty" - this means we've struck an inner bracket -whose current branch will already have been scanned. +can match the empty string or not. It is called from could_be_empty() +below and from compile_branch() when checking for an unlimited repeat of a +group that can match nothing. Note that first_significant_code() skips over +backward and negative forward assertions when its final argument is TRUE. If we +hit an unclosed bracket, we return "empty" - this means we've struck an inner +bracket whose current branch will already have been scanned. Arguments: code points to start of search @@ -1224,7 +1741,7 @@ could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) { register int c; -for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); +for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE); code < endcode; code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) { @@ -1232,33 +1749,69 @@ c = *code; - if (c >= OP_BRA) + /* Skip over forward assertions; the other assertions are skipped by + first_significant_code() with a TRUE final argument. */ + + if (c == OP_ASSERT) + { + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* Groups with zero repeats can of course be empty; skip them. */ + + if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO) + { + code += _pcre_OP_lengths[c]; + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* For other groups, scan the branches. */ + + if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE || c == OP_COND) { BOOL empty_branch; if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - /* Scan a closed bracket */ + /* If a conditional group has only one branch, there is a second, implied, + empty branch, so just skip over the conditional, because it could be empty. + Otherwise, scan the individual branches of the group. */ - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) - empty_branch = TRUE; + if (c == OP_COND && code[GET(code, 1)] != OP_ALT) code += GET(code, 1); + else + { + empty_branch = FALSE; + do + { + if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) + empty_branch = TRUE; + code += GET(code, 1); + } + while (*code == OP_ALT); + if (!empty_branch) return FALSE; /* All branches are non-empty */ } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - code += 1 + LINK_SIZE; + c = *code; + continue; } - else switch (c) + /* Handle the other opcodes */ + + switch (c) { - /* Check for quantifiers after a class */ + /* Check for quantifiers after a class. XCLASS is used for classes that + cannot be represented just by a bit map. This includes negated single + high-valued characters. The length in _pcre_OP_lengths[] is zero; the + actual length is stored in the compiled code, so we must update "code" + here. */ #ifdef SUPPORT_UTF8 case OP_XCLASS: - ccode = code + GET(code, 1); + ccode = code += GET(code, 1); goto CHECK_CLASS_REPEAT; #endif @@ -1302,21 +1855,45 @@ case OP_NOT_WORDCHAR: case OP_WORDCHAR: case OP_ANY: + case OP_ALLANY: case OP_ANYBYTE: case OP_CHAR: case OP_CHARNC: case OP_NOT: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_EXACT: case OP_NOTPLUS: case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: case OP_NOTEXACT: case OP_TYPEPLUS: case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: case OP_TYPEEXACT: return FALSE; + /* These are going to continue, as they may be empty, but we have to + fudge the length for the \p and \P cases. */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + /* Same for these */ + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; + break; + /* End of branch */ case OP_KET: @@ -1325,16 +1902,19 @@ case OP_ALT: return TRUE; - /* In UTF-8 mode, STAR, MINSTAR, QUERY, MINQUERY, UPTO, and MINUPTO may be - followed by a multibyte character */ + /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, + MINUPTO, and POSUPTO may be followed by a multibyte character */ #ifdef SUPPORT_UTF8 case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: if (utf8) while ((code[2] & 0xc0) == 0x80) code++; break; #endif @@ -1383,29 +1963,48 @@ *************************************************/ /* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by an -optional ^ and then a sequence of letters, terminated by a matching ":]" or -".]" or "=]". +encountered in a character class. It checks whether this is followed by a +sequence of characters terminated by a matching ":]" or ".]" or "=]". If we +reach an unescaped ']' without the special preceding character, return FALSE. + +Originally, this function only recognized a sequence of letters between the +terminators, but it seems that Perl recognizes any sequence of characters, +though of course unknown POSIX names are subsequently rejected. Perl gives an +"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE +didn't consider this to be a POSIX class. Likewise for [:1234:]. + +The problem in trying to be exactly like Perl is in the handling of escapes. We +have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX +class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code +below handles the special case of \], but does not try to do any other escape +processing. This makes it different from Perl for cases such as [:l\ower:] +where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize +"l\ower". This is a lesser evil that not diagnosing bad classes when Perl does, +I think. -Argument: +Arguments: ptr pointer to the initial [ endptr where to return the end pointer - cd pointer to compile data Returns: TRUE or FALSE */ static BOOL -check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd) +check_posix_syntax(const uschar *ptr, const uschar **endptr) { int terminator; /* Don't combine these lines; the Solaris cc */ terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -if (*(++ptr) == '^') ptr++; -while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; -if (*ptr == terminator && ptr[1] == ']') +for (++ptr; *ptr != 0; ptr++) { - *endptr = ptr; - return TRUE; + if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) ptr++; else + { + if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; + if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + { + *endptr = ptr; + return TRUE; + } + } } return FALSE; } @@ -1430,11 +2029,13 @@ static int check_posix_name(const uschar *ptr, int len) { +const char *pn = posix_names; register int yield = 0; while (posix_name_lengths[yield] != 0) { if (len == posix_name_lengths[yield] && - strncmp((const char *)ptr, posix_names[yield], len) == 0) return yield; + strncmp((const char *)ptr, pn, len) == 0) return yield; + pn += posix_name_lengths[yield] + 1; yield++; } return -1; @@ -1449,38 +2050,71 @@ that is referenced. This means that groups can be replicated for fixed repetition simply by copying (because the recursion is allowed to refer to earlier groups that are outside the current group). However, when a group is -optional (i.e. the minimum quantifier is zero), OP_BRAZERO is inserted before -it, after it has been compiled. This means that any OP_RECURSE items within it -that refer to the group itself or any contained groups have to have their -offsets adjusted. That is the job of this function. Before it is called, the -partially compiled regex must be temporarily terminated with OP_END. +optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is +inserted before it, after it has been compiled. This means that any OP_RECURSE +items within it that refer to the group itself or any contained groups have to +have their offsets adjusted. That one of the jobs of this function. Before it +is called, the partially compiled regex must be temporarily terminated with +OP_END. + +This function has been extended with the possibility of forward references for +recursions and subroutine calls. It must also check the list of such references +for the group we are dealing with. If it finds that one of the recursions in +the current group is on this list, it adjusts the offset in the list, not the +value in the reference (which is a group number). Arguments: group points to the start of the group adjust the amount by which the group is to be moved utf8 TRUE in UTF-8 mode cd contains pointers to tables etc. + save_hwm the hwm forward reference pointer at the start of the group Returns: nothing */ static void -adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd) +adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd, + uschar *save_hwm) { uschar *ptr = group; + while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) { - int offset = GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); - ptr += 1 + LINK_SIZE; - } -} + int offset; + uschar *hc; + /* See if this recursion is on the forward reference list. If so, adjust the + reference. */ + for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) + { + offset = GET(hc, 0); + if (cd->start_code + offset == ptr + 1) + { + PUT(hc, 0, offset + adjust); + break; + } + } -/************************************************* -* Insert an automatic callout point * -*************************************************/ + /* Otherwise, adjust the recursion offset if it's after the start of this + group. */ + + if (hc >= cd->hwm) + { + offset = GET(ptr, 1); + if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); + } + + ptr += 1 + LINK_SIZE; + } +} + + + +/************************************************* +* Insert an automatic callout point * +*************************************************/ /* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert callout points before each pattern item. @@ -1550,12 +2184,13 @@ */ static BOOL -get_othercase_range(int *cptr, int d, int *ocptr, int *odptr) +get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr, + unsigned int *odptr) { -int c, othercase, next; +unsigned int c, othercase, next; for (c = *cptr; c <= d; c++) - { if ((othercase = _pcre_ucp_othercase(c)) >= 0) break; } + { if ((othercase = UCD_OTHERCASE(c)) != c) break; } if (c > d) return FALSE; @@ -1564,7 +2199,7 @@ for (++c; c <= d; c++) { - if (_pcre_ucp_othercase(c) != next) break; + if (UCD_OTHERCASE(c) != next) break; next++; } @@ -1576,17 +2211,353 @@ #endif /* SUPPORT_UCP */ + +/************************************************* +* Check if auto-possessifying is possible * +*************************************************/ + +/* This function is called for unlimited repeats of certain items, to see +whether the next thing could possibly match the repeated item. If not, it makes +sense to automatically possessify the repeated item. + +Arguments: + op_code the repeated op code + this data for this item, depends on the opcode + utf8 TRUE in UTF-8 mode + utf8_char used for utf8 character bytes, NULL if not relevant + ptr next character in pattern + options options bits + cd contains pointers to tables etc. + +Returns: TRUE if possessifying is wanted +*/ + +static BOOL +check_auto_possessive(int op_code, int item, BOOL utf8, uschar *utf8_char, + const uschar *ptr, int options, compile_data *cd) +{ +int next; + +/* Skip whitespace and comments in extended mode */ + +if ((options & PCRE_EXTENDED) != 0) + { + for (;;) + { + while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; + if (*ptr == CHAR_NUMBER_SIGN) + { + while (*(++ptr) != 0) + if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + } + else break; + } + } + +/* If the next item is one that we can handle, get its value. A non-negative +value is a character, a negative value is an escape value. */ + +if (*ptr == CHAR_BACKSLASH) + { + int temperrorcode = 0; + next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE); + if (temperrorcode != 0) return FALSE; + ptr++; /* Point after the escape sequence */ + } + +else if ((cd->ctypes[*ptr] & ctype_meta) == 0) + { +#ifdef SUPPORT_UTF8 + if (utf8) { GETCHARINC(next, ptr); } else +#endif + next = *ptr++; + } + +else return FALSE; + +/* Skip whitespace and comments in extended mode */ + +if ((options & PCRE_EXTENDED) != 0) + { + for (;;) + { + while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; + if (*ptr == CHAR_NUMBER_SIGN) + { + while (*(++ptr) != 0) + if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + } + else break; + } + } + +/* If the next thing is itself optional, we have to give up. */ + +if (*ptr == CHAR_ASTERISK || *ptr == CHAR_QUESTION_MARK || + strncmp((char *)ptr, STR_LEFT_CURLY_BRACKET STR_0 STR_COMMA, 3) == 0) + return FALSE; + +/* Now compare the next item with the previous opcode. If the previous is a +positive single character match, "item" either contains the character or, if +"item" is greater than 127 in utf8 mode, the character's bytes are in +utf8_char. */ + + +/* Handle cases when the next item is a character. */ + +if (next >= 0) switch(op_code) + { + case OP_CHAR: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#else + (void)(utf8_char); /* Keep compiler happy by referencing function argument */ +#endif + return item != next; + + /* For CHARNC (caseless character) we must check the other case. If we have + Unicode property support, we can use it to test the other case of + high-valued characters. */ + + case OP_CHARNC: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#endif + if (item == next) return FALSE; +#ifdef SUPPORT_UTF8 + if (utf8) + { + unsigned int othercase; + if (next < 128) othercase = cd->fcc[next]; else +#ifdef SUPPORT_UCP + othercase = UCD_OTHERCASE((unsigned int)next); +#else + othercase = NOTACHAR; +#endif + return (unsigned int)item != othercase; + } + else +#endif /* SUPPORT_UTF8 */ + return (item != cd->fcc[next]); /* Non-UTF-8 mode */ + + /* For OP_NOT, "item" must be a single-byte character. */ + + case OP_NOT: + if (item == next) return TRUE; + if ((options & PCRE_CASELESS) == 0) return FALSE; +#ifdef SUPPORT_UTF8 + if (utf8) + { + unsigned int othercase; + if (next < 128) othercase = cd->fcc[next]; else +#ifdef SUPPORT_UCP + othercase = UCD_OTHERCASE(next); +#else + othercase = NOTACHAR; +#endif + return (unsigned int)item == othercase; + } + else +#endif /* SUPPORT_UTF8 */ + return (item == cd->fcc[next]); /* Non-UTF-8 mode */ + + case OP_DIGIT: + return next > 127 || (cd->ctypes[next] & ctype_digit) == 0; + + case OP_NOT_DIGIT: + return next <= 127 && (cd->ctypes[next] & ctype_digit) != 0; + + case OP_WHITESPACE: + return next > 127 || (cd->ctypes[next] & ctype_space) == 0; + + case OP_NOT_WHITESPACE: + return next <= 127 && (cd->ctypes[next] & ctype_space) != 0; + + case OP_WORDCHAR: + return next > 127 || (cd->ctypes[next] & ctype_word) == 0; + + case OP_NOT_WORDCHAR: + return next <= 127 && (cd->ctypes[next] & ctype_word) != 0; + + case OP_HSPACE: + case OP_NOT_HSPACE: + switch(next) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return op_code != OP_HSPACE; + default: + return op_code == OP_HSPACE; + } + + case OP_VSPACE: + case OP_NOT_VSPACE: + switch(next) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return op_code != OP_VSPACE; + default: + return op_code == OP_VSPACE; + } + + default: + return FALSE; + } + + +/* Handle the case when the next item is \d, \s, etc. */ + +switch(op_code) + { + case OP_CHAR: + case OP_CHARNC: +#ifdef SUPPORT_UTF8 + if (utf8 && item > 127) { GETCHAR(item, utf8_char); } +#endif + switch(-next) + { + case ESC_d: + return item > 127 || (cd->ctypes[item] & ctype_digit) == 0; + + case ESC_D: + return item <= 127 && (cd->ctypes[item] & ctype_digit) != 0; + + case ESC_s: + return item > 127 || (cd->ctypes[item] & ctype_space) == 0; + + case ESC_S: + return item <= 127 && (cd->ctypes[item] & ctype_space) != 0; + + case ESC_w: + return item > 127 || (cd->ctypes[item] & ctype_word) == 0; + + case ESC_W: + return item <= 127 && (cd->ctypes[item] & ctype_word) != 0; + + case ESC_h: + case ESC_H: + switch(item) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return -next != ESC_h; + default: + return -next == ESC_h; + } + + case ESC_v: + case ESC_V: + switch(item) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return -next != ESC_v; + default: + return -next == ESC_v; + } + + default: + return FALSE; + } + + case OP_DIGIT: + return next == -ESC_D || next == -ESC_s || next == -ESC_W || + next == -ESC_h || next == -ESC_v; + + case OP_NOT_DIGIT: + return next == -ESC_d; + + case OP_WHITESPACE: + return next == -ESC_S || next == -ESC_d || next == -ESC_w; + + case OP_NOT_WHITESPACE: + return next == -ESC_s || next == -ESC_h || next == -ESC_v; + + case OP_HSPACE: + return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w; + + case OP_NOT_HSPACE: + return next == -ESC_h; + + /* Can't have \S in here because VT matches \S (Perl anomaly) */ + case OP_VSPACE: + return next == -ESC_V || next == -ESC_d || next == -ESC_w; + + case OP_NOT_VSPACE: + return next == -ESC_v; + + case OP_WORDCHAR: + return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v; + + case OP_NOT_WORDCHAR: + return next == -ESC_w || next == -ESC_d; + + default: + return FALSE; + } + +/* Control does not reach here */ +} + + + /************************************************* * Compile one branch * *************************************************/ -/* Scan the pattern, compiling it into the code vector. If the options are +/* Scan the pattern, compiling it into the a vector. If the options are changed during the branch, the pointer is used to change the external options -bits. +bits. This function is used during the pre-compile phase when we are trying +to find out the amount of memory needed, as well as during the real compile +phase. The value of lengthptr distinguishes the two phases. Arguments: optionsptr pointer to the option bits - brackets points to number of extracting brackets used codeptr points to the pointer to the current code point ptrptr points to the current pattern pointer errorcodeptr points to error code variable @@ -1594,15 +2565,17 @@ reqbyteptr set to the last literal character required, else < 0 bcptr points to current branch chain cd contains pointers to tables etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase Returns: TRUE on success FALSE, with *errorcodeptr set non-zero on error */ static BOOL -compile_branch(int *optionsptr, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, int *firstbyteptr, - int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +compile_branch(int *optionsptr, uschar **codeptr, const uschar **ptrptr, + int *errorcodeptr, int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, + compile_data *cd, int *lengthptr) { int repeat_type, op_type; int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ @@ -1613,8 +2586,11 @@ int req_caseopt, reqvary, tempreqvary; int options = *optionsptr; int after_manual_callout = 0; +int length_prevgroup = 0; register int c; register uschar *code = *codeptr; +uschar *last_code = code; +uschar *orig_code = code; uschar *tempcode; BOOL inescq = FALSE; BOOL groupsetfirstbyte = FALSE; @@ -1622,15 +2598,22 @@ const uschar *tempptr; uschar *previous = NULL; uschar *previous_callout = NULL; +uschar *save_hwm = NULL; uschar classbits[32]; #ifdef SUPPORT_UTF8 BOOL class_utf8; BOOL utf8 = (options & PCRE_UTF8) != 0; uschar *class_utf8data; +uschar *class_utf8data_base; uschar utf8_char[6]; #else BOOL utf8 = FALSE; +uschar *utf8_char = NULL; +#endif + +#ifdef PCRE_DEBUG +if (lengthptr != NULL) DPRINTF((">> start branch\n")); #endif /* Set up the default and non-default settings for greediness */ @@ -1662,27 +2645,95 @@ for (;; ptr++) { BOOL negate_class; + BOOL should_flip_negation; BOOL possessive_quantifier; BOOL is_quantifier; + BOOL is_recurse; + BOOL reset_bracount; int class_charcount; int class_lastchar; int newoptions; int recno; + int refsign; int skipbytes; int subreqbyte; int subfirstbyte; + int terminator; int mclength; uschar mcbuffer[8]; - /* Next byte in the pattern */ + /* Get next byte in the pattern */ c = *ptr; + /* If we are in the pre-compile phase, accumulate the length used for the + previous cycle of this loop. */ + + if (lengthptr != NULL) + { +#ifdef PCRE_DEBUG + if (code > cd->hwm) cd->hwm = code; /* High water info */ +#endif + if (code > cd->start_workspace + COMPILE_WORK_SIZE) /* Check for overrun */ + { + *errorcodeptr = ERR52; + goto FAILED; + } + + /* There is at least one situation where code goes backwards: this is the + case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, + the class is simply eliminated. However, it is created first, so we have to + allow memory for it. Therefore, don't ever reduce the length at this point. + */ + + if (code < last_code) code = last_code; + + /* Paranoid check for integer overflow */ + + if (OFLOW_MAX - *lengthptr < code - last_code) + { + *errorcodeptr = ERR20; + goto FAILED; + } + + *lengthptr += code - last_code; + DPRINTF(("length=%d added %d c=%c\n", *lengthptr, code - last_code, c)); + + /* If "previous" is set and it is not at the start of the work space, move + it back to there, in order to avoid filling up the work space. Otherwise, + if "previous" is NULL, reset the current code pointer to the start. */ + + if (previous != NULL) + { + if (previous > orig_code) + { + memmove(orig_code, previous, code - previous); + code -= previous - orig_code; + previous = orig_code; + } + } + else code = orig_code; + + /* Remember where this code item starts so we can pick up the length + next time round. */ + + last_code = code; + } + + /* In the real compile phase, just check the workspace used by the forward + reference list. */ + + else if (cd->hwm > cd->start_workspace + COMPILE_WORK_SIZE) + { + *errorcodeptr = ERR52; + goto FAILED; + } + /* If in \Q...\E, check for the end; if not, we have a literal */ if (inescq && c != 0) { - if (c == '\\' && ptr[1] == 'E') + if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) { inescq = FALSE; ptr++; @@ -1692,7 +2743,8 @@ { if (previous_callout != NULL) { - complete_callout(previous_callout, ptr, cd); + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); previous_callout = NULL; } if ((options & PCRE_AUTO_CALLOUT) != 0) @@ -1707,13 +2759,15 @@ /* Fill in length of a previous callout, except when the next thing is a quantifier. */ - is_quantifier = c == '*' || c == '+' || c == '?' || - (c == '{' && is_counted_repeat(ptr+1)); + is_quantifier = + c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK || + (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1)); if (!is_quantifier && previous_callout != NULL && after_manual_callout-- <= 0) { - complete_callout(previous_callout, ptr, cd); + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); previous_callout = NULL; } @@ -1722,14 +2776,14 @@ if ((options & PCRE_EXTENDED) != 0) { if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') + if (c == CHAR_NUMBER_SIGN) { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) + while (*(++ptr) != 0) { - ptr += cd->nllen - 1; - continue; + if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } } + if (*ptr != 0) continue; + /* Else fall through to handle end of string */ c = 0; } @@ -1745,21 +2799,32 @@ switch(c) { - /* The branch terminates at end of string, |, or ). */ - - case 0: - case '|': - case ')': + /* ===================================================================*/ + case 0: /* The branch terminates at string end */ + case CHAR_VERTICAL_LINE: /* or | or ) */ + case CHAR_RIGHT_PARENTHESIS: *firstbyteptr = firstbyte; *reqbyteptr = reqbyte; *codeptr = code; *ptrptr = ptr; + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < code - last_code) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += code - last_code; /* To include callout length */ + DPRINTF((">> end branch\n")); + } return TRUE; + + /* ===================================================================*/ /* Handle single-character metacharacters. In multiline mode, ^ disables the setting of any following char as a first character. */ - case '^': + case CHAR_CIRCUMFLEX_ACCENT: if ((options & PCRE_MULTILINE) != 0) { if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; @@ -1768,7 +2833,7 @@ *code++ = OP_CIRC; break; - case '$': + case CHAR_DOLLAR_SIGN: previous = NULL; *code++ = OP_DOLL; break; @@ -1776,14 +2841,16 @@ /* There can never be a first char if '.' is first, whatever happens about repeats. The value of reqbyte doesn't change either. */ - case '.': + case CHAR_DOT: if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; zerofirstbyte = firstbyte; zeroreqbyte = reqbyte; previous = code; - *code++ = OP_ANY; + *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; break; + + /* ===================================================================*/ /* Character classes. If the included characters are all < 256, we build a 32-byte bitmap of the permitted characters, except in the special case where there is only one such character. For negated classes, we build the @@ -1794,78 +2861,133 @@ opcode is compiled. It may optionally have a bit map for characters < 256, but those above are are explicitly listed afterwards. A flag byte tells whether the bitmap is present, and whether this is a negated class or not. - */ - case '[': + In JavaScript compatibility mode, an isolated ']' causes an error. In + default (Perl) mode, it is treated as a data character. */ + + case CHAR_RIGHT_SQUARE_BRACKET: + if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) + { + *errorcodeptr = ERR64; + goto FAILED; + } + goto NORMAL_CHAR; + + case CHAR_LEFT_SQUARE_BRACKET: previous = code; /* PCRE supports POSIX class stuff inside a class. Perl gives an error if they are encountered at the top level, so we'll do that too. */ - if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) + if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && + check_posix_syntax(ptr, &tempptr)) { - *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31; + *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31; goto FAILED; } - /* If the first character is '^', set the negation flag and skip it. */ + /* If the first character is '^', set the negation flag and skip it. Also, + if the first few characters (either before or after ^) are \Q\E or \E we + skip them too. This makes for compatibility with Perl. */ - if ((c = *(++ptr)) == '^') + negate_class = FALSE; + for (;;) { - negate_class = TRUE; c = *(++ptr); + if (c == CHAR_BACKSLASH) + { + if (ptr[1] == CHAR_E) + ptr++; + else if (strncmp((const char *)ptr+1, + STR_Q STR_BACKSLASH STR_E, 3) == 0) + ptr += 3; + else + break; + } + else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) + negate_class = TRUE; + else break; } - else + + /* Empty classes are allowed in JavaScript compatibility mode. Otherwise, + an initial ']' is taken as a data character -- the code below handles + that. In JS mode, [] must always fail, so generate OP_FAIL, whereas + [^] must match any character, so generate OP_ALLANY. */ + + if (c == CHAR_RIGHT_SQUARE_BRACKET && + (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) { - negate_class = FALSE; + *code++ = negate_class? OP_ALLANY : OP_FAIL; + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + zerofirstbyte = firstbyte; + break; } + /* If a class contains a negative special such as \S, we need to flip the + negation flag at the end, so that support for characters > 255 works + correctly (they are all included in the class). */ + + should_flip_negation = FALSE; + /* Keep a count of chars with values < 256 so that we can optimize the case - of just a single character (as long as it's < 256). For higher valued UTF-8 - characters, we don't yet do any optimization. */ + of just a single character (as long as it's < 256). However, For higher + valued UTF-8 characters, we don't yet do any optimization. */ class_charcount = 0; class_lastchar = -1; + /* Initialize the 32-char bit map to all zeros. We build the map in a + temporary bit of memory, in case the class contains only 1 character (less + than 256), because in that case the compiled code doesn't use the bit map. + */ + + memset(classbits, 0, 32 * sizeof(uschar)); + #ifdef SUPPORT_UTF8 class_utf8 = FALSE; /* No chars >= 256 */ - class_utf8data = code + LINK_SIZE + 34; /* For UTF-8 items */ + class_utf8data = code + LINK_SIZE + 2; /* For UTF-8 items */ + class_utf8data_base = class_utf8data; /* For resetting in pass 1 */ #endif - /* Initialize the 32-char bit map to all zeros. We have to build the - map in a temporary bit of store, in case the class contains only 1 - character (< 256), because in that case the compiled code doesn't use the - bit map. */ - - memset(classbits, 0, 32 * sizeof(uschar)); - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. The first pass - through the regex checked the overall syntax, so we don't need to be very - strict here. At the start of the loop, c contains the first byte of the - character. */ + means that an initial ] is taken as a data character. At the start of the + loop, c contains the first byte of the character. */ - do + if (c != 0) do { + const uschar *oldptr; + #ifdef SUPPORT_UTF8 if (utf8 && c > 127) { /* Braces are required because the */ GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ } + + /* In the pre-compile phase, accumulate the length of any UTF-8 extra + data and reset the pointer. This is so that very large classes that + contain a zillion UTF-8 characters no longer overwrite the work space + (which is on the stack). */ + + if (lengthptr != NULL) + { + *lengthptr += class_utf8data - class_utf8data_base; + class_utf8data = class_utf8data_base; + } + #endif /* Inside \Q...\E everything is literal except \E */ if (inescq) { - if (c == '\\' && ptr[1] == 'E') + if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) /* If we are at \E */ { - inescq = FALSE; - ptr++; - continue; + inescq = FALSE; /* Reset literal state */ + ptr++; /* Skip the 'E' */ + continue; /* Carry on with next */ } - else goto LONE_SINGLE_CHARACTER; + goto CHECK_RANGE; /* Could be range if \E follows */ } /* Handle POSIX class names. Perl allows a negation extension of the @@ -1874,25 +2996,26 @@ [.ch.] and [=ch=] ("collating elements") and fault them, as Perl 5.6 and 5.8 do. */ - if (c == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) + if (c == CHAR_LEFT_SQUARE_BRACKET && + (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr)) { BOOL local_negate = FALSE; int posix_class, taboffset, tabopt; register const uschar *cbits = cd->cbits; uschar pbits[32]; - if (ptr[1] != ':') + if (ptr[1] != CHAR_COLON) { *errorcodeptr = ERR31; goto FAILED; } ptr += 2; - if (*ptr == '^') + if (*ptr == CHAR_CIRCUMFLEX_ACCENT) { local_negate = TRUE; + should_flip_negation = TRUE; /* Note negative special */ ptr++; } @@ -1956,40 +3079,46 @@ } /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. Escaped items are checked for - validity in the pre-compiling pass. The sequence \b is a special case. - Inside a class (and only there) it is treated as backspace. Elsewhere - it marks a word boundary. Other escapes have preset maps ready to - or into the one we are building. We assume they have more than one + of the specials, which just set a flag. The sequence \b is a special + case. Inside a class (and only there) it is treated as backspace. + Elsewhere it marks a word boundary. Other escapes have preset maps ready + to 'or' into the one we are building. We assume they have more than one character in them, so set class_charcount bigger than one. */ - if (c == '\\') + if (c == CHAR_BACKSLASH) { - c = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); + if (*errorcodeptr != 0) goto FAILED; - if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ - else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ + if (-c == ESC_b) c = CHAR_BS; /* \b is backspace in a class */ + else if (-c == ESC_X) c = CHAR_X; /* \X is literal X in a class */ + else if (-c == ESC_R) c = CHAR_R; /* \R is literal R in a class */ else if (-c == ESC_Q) /* Handle start of quoted string */ { - if (ptr[1] == '\\' && ptr[2] == 'E') + if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) { ptr += 2; /* avoid empty string */ } else inescq = TRUE; continue; } + else if (-c == ESC_E) continue; /* Ignore orphan \E */ if (c < 0) { register const uschar *cbits = cd->cbits; class_charcount += 2; /* Greater than 1 is what matters */ - switch (-c) + + /* Save time by not doing this in the pre-compile phase. */ + + if (lengthptr == NULL) switch (-c) { case ESC_d: for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; continue; case ESC_D: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; continue; @@ -1998,6 +3127,7 @@ continue; case ESC_W: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; continue; @@ -2007,56 +3137,227 @@ continue; case ESC_S: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ continue; -#ifdef SUPPORT_UCP - case ESC_p: - case ESC_P: + default: /* Not recognized; fall through */ + break; /* Need "default" setting to stop compiler warning. */ + } + + /* In the pre-compile phase, just do the recognition. */ + + else if (c == -ESC_d || c == -ESC_D || c == -ESC_w || + c == -ESC_W || c == -ESC_s || c == -ESC_S) continue; + + /* We need to deal with \H, \h, \V, and \v in both phases because + they use extra memory. */ + + if (-c == ESC_h) + { + SETBIT(classbits, 0x09); /* VT */ + SETBIT(classbits, 0x20); /* SPACE */ + SETBIT(classbits, 0xa0); /* NSBP */ +#ifdef SUPPORT_UTF8 + if (utf8) { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; class_utf8 = TRUE; - *class_utf8data++ = ((-c == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_utf8data++ = ptype; - *class_utf8data++ = pdata; - class_charcount -= 2; /* Not a < 256 character */ + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data); } - continue; #endif + continue; + } - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ + if (-c == ESC_H) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x09/8: x ^= 1 << (0x09%8); break; + case 0x20/8: x ^= 1 << (0x20%8); break; + case 0xa0/8: x ^= 1 << (0xa0%8); break; + default: break; + } + classbits[c] |= x; + } - default: - if ((options & PCRE_EXTRA) != 0) +#ifdef SUPPORT_UTF8 + if (utf8) { - *errorcodeptr = ERR7; - goto FAILED; + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); } - c = *ptr; /* The final character */ - class_charcount -= 2; /* Undo the default count from above */ +#endif + continue; } - } - /* Fall through if we have a single character (c >= 0). This may be - > 256 in UTF-8 mode. */ + if (-c == ESC_v) + { + SETBIT(classbits, 0x0a); /* LF */ + SETBIT(classbits, 0x0b); /* VT */ + SETBIT(classbits, 0x0c); /* FF */ + SETBIT(classbits, 0x0d); /* CR */ + SETBIT(classbits, 0x85); /* NEL */ +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + } +#endif + continue; + } - } /* End of backslash handling */ + if (-c == ESC_V) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x0a/8: x ^= 1 << (0x0a%8); + x ^= 1 << (0x0b%8); + x ^= 1 << (0x0c%8); + x ^= 1 << (0x0d%8); + break; + case 0x85/8: x ^= 1 << (0x85%8); break; + default: break; + } + classbits[c] |= x; + } - /* A single character may be followed by '-' to form a range. However, +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); + } +#endif + continue; + } + + /* We need to deal with \P and \p in both phases. */ + +#ifdef SUPPORT_UCP + if (-c == ESC_p || -c == ESC_P) + { + BOOL negated; + int pdata; + int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + if (ptype < 0) goto FAILED; + class_utf8 = TRUE; + *class_utf8data++ = ((-c == ESC_p) != negated)? + XCL_PROP : XCL_NOTPROP; + *class_utf8data++ = ptype; + *class_utf8data++ = pdata; + class_charcount -= 2; /* Not a < 256 character */ + continue; + } +#endif + /* Unrecognized escapes are faulted if PCRE is running in its + strict mode. By default, for compatibility with Perl, they are + treated as literals. */ + + if ((options & PCRE_EXTRA) != 0) + { + *errorcodeptr = ERR7; + goto FAILED; + } + + class_charcount -= 2; /* Undo the default count from above */ + c = *ptr; /* Get the final character and fall through */ + } + + /* Fall through if we have a single character (c >= 0). This may be + greater than 256 in UTF-8 mode. */ + + } /* End of backslash handling */ + + /* A single character may be followed by '-' to form a range. However, Perl does not permit ']' to be the end of the range. A '-' character - here is treated as a literal. */ + at the end is treated as a literal. Perl ignores orphaned \E sequences + entirely. The code for handling \Q and \E is messy. */ + + CHECK_RANGE: + while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) + { + inescq = FALSE; + ptr += 2; + } + + oldptr = ptr; + + /* Remember \r or \n */ - if (ptr[1] == '-' && ptr[2] != ']') + if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; + + /* Check for range */ + + if (!inescq && ptr[1] == CHAR_MINUS) { int d; ptr += 2; + while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2; + + /* If we hit \Q (not followed by \E) at this point, go into escaped + mode. */ + + while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q) + { + ptr += 2; + if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) + { ptr += 2; continue; } + inescq = TRUE; + break; + } + + if (*ptr == 0 || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET)) + { + ptr = oldptr; + goto LONE_SINGLE_CHARACTER; + } #ifdef SUPPORT_UTF8 if (utf8) @@ -2071,30 +3372,41 @@ not any of the other escapes. Perl 5.6 treats a hyphen as a literal in such circumstances. */ - if (d == '\\') + if (!inescq && d == CHAR_BACKSLASH) { - const uschar *oldptr = ptr; - d = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); + if (*errorcodeptr != 0) goto FAILED; - /* \b is backslash; \X is literal X; any other special means the '-' - was literal */ + /* \b is backspace; \X is literal X; \R is literal R; any other + special means the '-' was literal */ if (d < 0) { - if (d == -ESC_b) d = '\b'; - else if (d == -ESC_X) d = 'X'; else + if (d == -ESC_b) d = CHAR_BS; + else if (d == -ESC_X) d = CHAR_X; + else if (d == -ESC_R) d = CHAR_R; else { - ptr = oldptr - 2; + ptr = oldptr; goto LONE_SINGLE_CHARACTER; /* A few lines below */ } } } - /* The check that the two values are in the correct order happens in - the pre-pass. Optimize one-character ranges */ + /* Check that the two values are in the correct order. Optimize + one-character ranges */ + + if (d < c) + { + *errorcodeptr = ERR8; + goto FAILED; + } if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ + /* Remember \r or \n */ + + if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; + /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless matching, we have to use an XCLASS with extra data items. Caseless matching for characters > 127 is available only if UCP support is @@ -2112,19 +3424,23 @@ #ifdef SUPPORT_UCP if ((options & PCRE_CASELESS) != 0) { - int occ, ocd; - int cc = c; - int origd = d; + unsigned int occ, ocd; + unsigned int cc = c; + unsigned int origd = d; while (get_othercase_range(&cc, origd, &occ, &ocd)) { - if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */ + if (occ >= (unsigned int)c && + ocd <= (unsigned int)d) + continue; /* Skip embedded ranges */ - if (occ < c && ocd >= c - 1) /* Extend the basic range */ + if (occ < (unsigned int)c && + ocd >= (unsigned int)c - 1) /* Extend the basic range */ { /* if there is overlap, */ c = occ; /* noting that if occ < c */ continue; /* we can't have ocd > d */ } /* because a subrange is */ - if (ocd > d && occ <= d + 1) /* always shorter than */ + if (ocd > (unsigned int)d && + occ <= (unsigned int)d + 1) /* always shorter than */ { /* the basic range. */ d = ocd; continue; @@ -2172,7 +3488,12 @@ ranges that lie entirely within 0-127 when there is UCP support; else for partial ranges without UCP support. */ - for (; c <= d; c++) + class_charcount += d - c + 1; + class_lastchar = d; + + /* We can save a bit of time by skipping this in the pre-compile. */ + + if (lengthptr == NULL) for (; c <= d; c++) { classbits[c/8] |= (1 << (c&7)); if ((options & PCRE_CASELESS) != 0) @@ -2180,8 +3501,6 @@ int uc = cd->fcc[c]; /* flip case */ classbits[uc/8] |= (1 << (uc&7)); } - class_charcount++; /* in case a one-char range */ - class_lastchar = c; } continue; /* Go get the next char in the class */ @@ -2205,8 +3524,8 @@ #ifdef SUPPORT_UCP if ((options & PCRE_CASELESS) != 0) { - int othercase; - if ((othercase = _pcre_ucp_othercase(c)) >= 0) + unsigned int othercase; + if ((othercase = UCD_OTHERCASE(c)) != c) { *class_utf8data++ = XCL_SINGLE; class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); @@ -2231,17 +3550,44 @@ } } - /* Loop until ']' reached; the check for end of string happens inside the - loop. This "while" is the end of the "do" above. */ + /* Loop until ']' reached. This "while" is the end of the "do" above. */ + + while ((c = *(++ptr)) != 0 && (c != CHAR_RIGHT_SQUARE_BRACKET || inescq)); + + if (c == 0) /* Missing terminating ']' */ + { + *errorcodeptr = ERR6; + goto FAILED; + } + + +/* This code has been disabled because it would mean that \s counts as +an explicit \r or \n reference, and that's not really what is wanted. Now +we set the flag only if there is a literal "\r" or "\n" in the class. */ + +#if 0 + /* Remember whether \r or \n are in this class */ + + if (negate_class) + { + if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF; + } + else + { + if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF; + } +#endif - while ((c = *(++ptr)) != ']' || inescq); /* If class_charcount is 1, we saw precisely one character whose value is - less than 256. In non-UTF-8 mode we can always optimize. In UTF-8 mode, we - can optimize the negative case only if there were no characters >= 128 - because OP_NOT and the related opcodes like OP_NOTSTAR operate on - single-bytes only. This is an historical hangover. Maybe one day we can - tidy these opcodes to handle multi-byte characters. + less than 256. As long as there were no characters >= 128 and there was no + use of \p or \P, in other words, no use of any XCLASS features, we can + optimize. + + In UTF-8 mode, we can optimize the negative case only if there were no + characters >= 128 because OP_NOT and the related opcodes like OP_NOTSTAR + operate on single-bytes only. This is an historical hangover. Maybe one day + we can tidy these opcodes to handle multi-byte characters. The optimization throws away the bit map. We turn the item into a 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note @@ -2251,10 +3597,8 @@ reqbyte, save the previous value for reinstating. */ #ifdef SUPPORT_UTF8 - if (class_charcount == 1 && - (!utf8 || - (!class_utf8 && (!negate_class || class_lastchar < 128)))) - + if (class_charcount == 1 && !class_utf8 && + (!utf8 || !negate_class || class_lastchar < 128)) #else if (class_charcount == 1) #endif @@ -2297,35 +3641,31 @@ zeroreqbyte = reqbyte; /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode. If there are no characters < 256, - we can omit the bitmap. */ + extended class, with its own opcode, unless there was a negated special + such as \S in the class, because in that case all characters > 255 are in + the class, so any that were explicitly given as well can be ignored. If + (when there are explicit characters > 255 that must be listed) there are no + characters < 256, we can omit the bitmap in the actual compiled code. */ #ifdef SUPPORT_UTF8 - if (class_utf8) + if (class_utf8 && !should_flip_negation) { *class_utf8data++ = XCL_END; /* Marks the end of extra data */ *code++ = OP_XCLASS; code += LINK_SIZE; *code = negate_class? XCL_NOT : 0; - /* If the map is required, install it, and move on to the end of - the extra data */ + /* If the map is required, move up the extra data to make room for it; + otherwise just move the code pointer to the end of the extra data. */ if (class_charcount > 0) { *code++ |= XCL_MAP; + memmove(code + 32, code, class_utf8data - code); memcpy(code, classbits, 32); - code = class_utf8data; - } - - /* If the map is not required, slide down the extra data. */ - - else - { - int len = class_utf8data - (code + 33); - memmove(code + 1, code + 33, len); - code += len + 1; + code = class_utf8data + 32; } + else code = class_utf8data; /* Now fill in the complete length of the item */ @@ -2334,44 +3674,46 @@ } #endif - /* If there are no characters > 255, negate the 32-byte map if necessary, - and copy it into the code vector. If this is the first thing in the branch, - there can be no first char setting, whatever the repeat count. Any reqbyte - setting must remain unchanged after any kind of repeat. */ + /* If there are no characters > 255, set the opcode to OP_CLASS or + OP_NCLASS, depending on whether the whole class was negated and whether + there were negative specials such as \S in the class. Then copy the 32-byte + map into the code vector, negating it if necessary. */ + *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; if (negate_class) { - *code++ = OP_NCLASS; - for (c = 0; c < 32; c++) code[c] = ~classbits[c]; + if (lengthptr == NULL) /* Save time in the pre-compile phase */ + for (c = 0; c < 32; c++) code[c] = ~classbits[c]; } else { - *code++ = OP_CLASS; memcpy(code, classbits, 32); } code += 32; break; + + /* ===================================================================*/ /* Various kinds of repeat; '{' is not necessarily a quantifier, but this has been tested above. */ - case '{': + case CHAR_LEFT_CURLY_BRACKET: if (!is_quantifier) goto NORMAL_CHAR; ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); if (*errorcodeptr != 0) goto FAILED; goto REPEAT; - case '*': + case CHAR_ASTERISK: repeat_min = 0; repeat_max = -1; goto REPEAT; - case '+': + case CHAR_PLUS: repeat_min = 1; repeat_max = -1; goto REPEAT; - case '?': + case CHAR_QUESTION_MARK: repeat_min = 0; repeat_max = 1; @@ -2406,33 +3748,19 @@ but if PCRE_UNGREEDY is set, it works the other way round. We change the repeat type to the non-default. */ - if (ptr[1] == '+') + if (ptr[1] == CHAR_PLUS) { repeat_type = 0; /* Force greedy */ possessive_quantifier = TRUE; ptr++; } - else if (ptr[1] == '?') + else if (ptr[1] == CHAR_QUESTION_MARK) { repeat_type = greedy_non_default; ptr++; } else repeat_type = greedy_default; - /* If previous was a recursion, we need to wrap it inside brackets so that - it can be replicated if necessary. */ - - if (*previous == OP_RECURSE) - { - memmove(previous + 1 + LINK_SIZE, previous, 1 + LINK_SIZE); - code += 1 + LINK_SIZE; - *previous = OP_BRA; - PUT(previous, 1, code - previous); - *code = OP_KET; - PUT(code, 1, code - previous); - code += 1 + LINK_SIZE; - } - /* If previous was a character match, abolish the item and generate a repeat item instead. If a char item has a minumum of more than one, ensure that it is set in reqbyte - it might not be if a sequence such as x{3} is @@ -2466,18 +3794,40 @@ if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; } + /* If the repetition is unlimited, it pays to see if the next thing on + the line is something that cannot possibly match this character. If so, + automatically possessifying this item gains some performance in the case + where the match fails. */ + + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(*previous, c, utf8, utf8_char, ptr + 1, + options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } + goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ } /* If previous was a single negated character ([^a] or similar), we use one of the special opcodes, replacing it. The code is shared with single- character repeats by setting opt_type to add a suitable offset into - repeat_type. OP_NOT is currently used only for single-byte chars. */ + repeat_type. We can also test for auto-possessification. OP_NOT is + currently used only for single-byte chars. */ else if (*previous == OP_NOT) { op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ c = previous[1]; + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(OP_NOT, c, utf8, NULL, ptr + 1, options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } goto OUTPUT_SINGLE_REPEAT; } @@ -2495,6 +3845,14 @@ op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ c = *previous; + if (!possessive_quantifier && + repeat_max < 0 && + check_auto_possessive(c, 0, utf8, NULL, ptr + 1, options, cd)) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + } + OUTPUT_SINGLE_REPEAT: if (*previous == OP_PROP || *previous == OP_NOTPROP) { @@ -2514,7 +3872,7 @@ /* All real repeats make it impossible to handle partial matching (maybe one day we will be able to remove this restriction). */ - if (repeat_max != 1) cd->nopartial = TRUE; + if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; /* Combine the op_type with the repeat_type */ @@ -2535,7 +3893,7 @@ } /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item it + maximum is unlimited, we use OP_PLUS. Otherwise, the original item is left in place and, if the maximum is greater than 1, we use OP_UPTO with one less than the maximum. */ @@ -2588,7 +3946,8 @@ } /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. */ + preceded by the character, for the previously inserted code. If the + UPTO is just for 1 instance, we can use QUERY instead. */ else if (repeat_max != repeat_min) { @@ -2607,8 +3966,16 @@ *code++ = prop_value; } repeat_max -= repeat_min; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); + + if (repeat_max == 1) + { + *code++ = OP_QUERY + repeat_type; + } + else + { + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } } } @@ -2655,7 +4022,7 @@ /* All real repeats make it impossible to handle partial matching (maybe one day we will be able to remove this restriction). */ - if (repeat_max != 1) cd->nopartial = TRUE; + if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; if (repeat_min == 0 && repeat_max == -1) *code++ = OP_CRSTAR + repeat_type; @@ -2675,14 +4042,22 @@ /* If previous was a bracket group, we may have to replicate it in certain cases. */ - else if (*previous >= OP_BRA || *previous == OP_ONCE || - *previous == OP_COND) + else if (*previous == OP_BRA || *previous == OP_CBRA || + *previous == OP_ONCE || *previous == OP_COND) { register int i; int ketoffset = 0; int len = code - previous; uschar *bralink = NULL; + /* Repeating a DEFINE group is pointless */ + + if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) + { + *errorcodeptr = ERR55; + goto FAILED; + } + /* If the maximum repeat count is unlimited, find the end of the bracket by scanning through from the start, and compute the offset back to it from the current code pointer. There may be an OP_OPT setting following @@ -2705,27 +4080,38 @@ if (repeat_min == 0) { - /* If the maximum is also zero, we just omit the group from the output - altogether. */ + /* If the maximum is also zero, we used to just omit the group from the + output altogether, like this: - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } + ** if (repeat_max == 0) + ** { + ** code = previous; + ** goto END_REPEAT; + ** } + + However, that fails when a group is referenced as a subroutine from + elsewhere in the pattern, so now we stick in OP_SKIPZERO in front of it + so that it is skipped on execution. As we don't have a list of which + groups are referenced, we cannot do this selectively. + + If the maximum is 1 or unlimited, we just have to stick in the BRAZERO + and do no more at this point. However, we do need to adjust any + OP_RECURSE calls inside the group that refer to the group itself or any + internal or forward referenced group, because the offset is from the + start of the whole regex. Temporarily terminate the pattern while doing + this. */ - /* If the maximum is 1 or unlimited, we just have to stick in the - BRAZERO and do no more at this point. However, we do need to adjust - any OP_RECURSE calls inside the group that refer to the group itself or - any internal group, because the offset is from the start of the whole - regex. Temporarily terminate the pattern while doing this. */ - - if (repeat_max <= 1) + if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ { *code = OP_END; - adjust_recurse(previous, 1, utf8, cd); + adjust_recurse(previous, 1, utf8, cd, save_hwm); memmove(previous+1, previous, len); code++; + if (repeat_max == 0) + { + *previous++ = OP_SKIPZERO; + goto END_REPEAT; + } *previous++ = OP_BRAZERO + repeat_type; } @@ -2741,7 +4127,7 @@ { int offset; *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd); + adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd, save_hwm); memmove(previous + 2 + LINK_SIZE, previous, len); code += 2 + LINK_SIZE; *previous++ = OP_BRAZERO + repeat_type; @@ -2761,19 +4147,52 @@ /* If the minimum is greater than zero, replicate the group as many times as necessary, and adjust the maximum to the number of subsequent copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. */ + set a required char, copy the latter from the former. If there are any + forward reference subroutine calls in the group, there will be entries on + the workspace list; replicate these with an appropriate increment. */ else { if (repeat_min > 1) { - if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; - for (i = 1; i < repeat_min; i++) + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. Do some paranoid checks for + potential integer overflow. */ + + if (lengthptr != NULL) + { + int delta = (repeat_min - 1)*length_prevgroup; + if ((double)(repeat_min - 1)*(double)length_prevgroup > + (double)INT_MAX || + OFLOW_MAX - *lengthptr < delta) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += delta; + } + + /* This is compiling for real */ + + else { - memcpy(code, previous, len); - code += len; + if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; + for (i = 1; i < repeat_min; i++) + { + uschar *hc; + uschar *this_hwm = cd->hwm; + memcpy(code, previous, len); + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; + code += len; + } } } + if (repeat_max > 0) repeat_max -= repeat_min; } @@ -2781,12 +4200,39 @@ the maximum is limited, it replicates the group in a nested fashion, remembering the bracket starts on a stack. In the case of a zero minimum, the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. */ + the number of additional copies needed. Again, we must remember to + replicate entries on the forward reference list. */ if (repeat_max >= 0) { - for (i = repeat_max - 1; i >= 0; i--) + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. For each repetition we must add 1 + to the length for BRAZERO and for all but the last repetition we must + add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some + paranoid checks to avoid integer overflow. */ + + if (lengthptr != NULL && repeat_max > 0) + { + int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - + 2 - 2*LINK_SIZE; /* Last one doesn't nest */ + if ((double)repeat_max * + (double)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) + > (double)INT_MAX || + OFLOW_MAX - *lengthptr < delta) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += delta; + } + + /* This is compiling for real */ + + else for (i = repeat_max - 1; i >= 0; i--) { + uschar *hc; + uschar *this_hwm = cd->hwm; + *code++ = OP_BRAZERO + repeat_type; /* All but the final copy start a new nesting, maintaining the @@ -2802,6 +4248,12 @@ } memcpy(code, previous, len); + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; code += len; } @@ -2824,11 +4276,43 @@ /* If the maximum is unlimited, set a repeater in the final copy. We can't just offset backwards from the current code point, because we don't know if there's been an options resetting after the ket. The - correct offset was computed above. */ + correct offset was computed above. - else code[-ketoffset] = OP_KETRMAX + repeat_type; + Then, when we are doing the actual compile phase, check to see whether + this group is a non-atomic one that could match an empty string. If so, + convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so + that runtime checking can be done. [This check is also applied to + atomic groups at runtime, but in a different way.] */ + + else + { + uschar *ketcode = code - ketoffset; + uschar *bracode = ketcode - GET(ketcode, 1); + *ketcode = OP_KETRMAX + repeat_type; + if (lengthptr == NULL && *bracode != OP_ONCE) + { + uschar *scode = bracode; + do + { + if (could_be_empty_branch(scode, ketcode, utf8)) + { + *bracode += OP_SBRA - OP_BRA; + break; + } + scode += GET(scode, 1); + } + while (*scode == OP_ALT); + } + } } + /* If previous is OP_FAIL, it was generated by an empty class [] in + JavaScript mode. The other ways in which OP_FAIL can be generated, that is + by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat" + error above. We can just ignore the repeat in JS case. */ + + else if (*previous == OP_FAIL) goto END_REPEAT; + /* Else there's some kind of shambles */ else @@ -2837,22 +4321,55 @@ goto FAILED; } - /* If the character following a repeat is '+', we wrap the entire repeated - item inside OP_ONCE brackets. This is just syntactic sugar, taken from - Sun's Java package. The repeated item starts at tempcode, not at previous, - which might be the first part of a string whose (former) last char we - repeated. However, we don't support '+' after a greediness '?'. */ + /* If the character following a repeat is '+', or if certain optimization + tests above succeeded, possessive_quantifier is TRUE. For some of the + simpler opcodes, there is an special alternative opcode for this. For + anything else, we wrap the entire repeated item inside OP_ONCE brackets. + The '+' notation is just syntactic sugar, taken from Sun's Java package, + but the special opcodes can optimize it a bit. The repeated item starts at + tempcode, not at previous, which might be the first part of a string whose + (former) last char we repeated. + + Possessifying an 'exact' quantifier has no effect, so we can ignore it. But + an 'upto' may follow. We skip over an 'exact' item, and then test the + length of what remains before proceeding. */ if (possessive_quantifier) { - int len = code - tempcode; - memmove(tempcode + 1+LINK_SIZE, tempcode, len); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); + int len; + if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT || + *tempcode == OP_NOTEXACT) + tempcode += _pcre_OP_lengths[*tempcode] + + ((*tempcode == OP_TYPEEXACT && + (tempcode[3] == OP_PROP || tempcode[3] == OP_NOTPROP))? 2:0); + len = code - tempcode; + if (len > 0) switch (*tempcode) + { + case OP_STAR: *tempcode = OP_POSSTAR; break; + case OP_PLUS: *tempcode = OP_POSPLUS; break; + case OP_QUERY: *tempcode = OP_POSQUERY; break; + case OP_UPTO: *tempcode = OP_POSUPTO; break; + + case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; + case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; + case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; + case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; + + case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; + case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; + case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; + case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; + + default: + memmove(tempcode + 1+LINK_SIZE, tempcode, len); + code += 1 + LINK_SIZE; + len += 1 + LINK_SIZE; + tempcode[0] = OP_ONCE; + *code++ = OP_KET; + PUTINC(code, 0, len); + PUT(tempcode, 1, len); + break; + } } /* In all case we no longer have a previous item. We also set the @@ -2865,230 +4382,516 @@ break; - /* Start of nested bracket sub-expression, or comment or lookahead or - lookbehind or option setting or condition. First deal with special things - that can come after a bracket; all are introduced by ?, and the appearance - of any of them means that this is not a referencing group. They were - checked for validity in the first pass over the string, so we don't have to - check for syntax errors here. */ + /* ===================================================================*/ + /* Start of nested parenthesized sub-expression, or comment or lookahead or + lookbehind or option setting or condition or all the other extended + parenthesis forms. */ - case '(': + case CHAR_LEFT_PARENTHESIS: newoptions = options; skipbytes = 0; + bravalue = OP_CBRA; + save_hwm = cd->hwm; + reset_bracount = FALSE; + + /* First deal with various "verbs" that can be introduced by '*'. */ + + if (*(++ptr) == CHAR_ASTERISK && (cd->ctypes[ptr[1]] & ctype_letter) != 0) + { + int i, namelen; + const char *vn = verbnames; + const uschar *name = ++ptr; + previous = NULL; + while ((cd->ctypes[*++ptr] & ctype_letter) != 0) {}; + if (*ptr == CHAR_COLON) + { + *errorcodeptr = ERR59; /* Not supported */ + goto FAILED; + } + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR60; + goto FAILED; + } + namelen = ptr - name; + for (i = 0; i < verbcount; i++) + { + if (namelen == verbs[i].len && + strncmp((char *)name, vn, namelen) == 0) + { + *code = verbs[i].op; + if (*code++ == OP_ACCEPT) cd->had_accept = TRUE; + break; + } + vn += verbs[i].len + 1; + } + if (i < verbcount) continue; + *errorcodeptr = ERR60; + goto FAILED; + } + + /* Deal with the extended parentheses; all are introduced by '?', and the + appearance of any of them means that this is not a capturing group. */ - if (*(++ptr) == '?') + else if (*ptr == CHAR_QUESTION_MARK) { - int set, unset; + int i, set, unset, namelen; int *optset; + const uschar *name; + uschar *slot; switch (*(++ptr)) { - case '#': /* Comment; skip to ket */ + case CHAR_NUMBER_SIGN: /* Comment; skip to ket */ ptr++; - while (*ptr != ')') ptr++; + while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; + if (*ptr == 0) + { + *errorcodeptr = ERR18; + goto FAILED; + } continue; - case ':': /* Non-extracting bracket */ + + /* ------------------------------------------------------------ */ + case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ + reset_bracount = TRUE; + /* Fall through */ + + /* ------------------------------------------------------------ */ + case CHAR_COLON: /* Non-capturing bracket */ bravalue = OP_BRA; ptr++; break; - case '(': + + /* ------------------------------------------------------------ */ + case CHAR_LEFT_PARENTHESIS: bravalue = OP_COND; /* Conditional group */ - /* A condition can be a number, referring to a numbered group, a name, - referring to a named group, 'R', referring to recursion, or an - assertion. There are two unfortunate ambiguities, caused by history. - (a) 'R' can be the recursive thing or the name 'R', and (b) a number - could be a name that consists of digits. In both cases, we look for a - name first; if not found, we try the other cases. If the first - character after (?( is a word character, we know the rest up to ) will - also be word characters because the syntax was checked in the first - pass. */ - - if ((cd->ctypes[ptr[1]] & ctype_word) != 0) - { - int i, namelen; - int condref = 0; - const uschar *name; - uschar *slot = cd->name_table; + /* A condition can be an assertion, a number (referring to a numbered + group), a name (referring to a named group), or 'R', referring to + recursion. R<digits> and R&name are also permitted for recursion tests. + + There are several syntaxes for testing a named group: (?(name)) is used + by Python; Perl 5.10 onwards uses (?(<name>) or (?('name')). + + There are two unfortunate ambiguities, caused by history. (a) 'R' can + be the recursive thing or the name 'R' (and similarly for 'R' followed + by digits), and (b) a number could be a name that consists of digits. + In both cases, we look for a name first; if not found, we try the other + cases. */ + + /* For conditions that are assertions, check the syntax, and then exit + the switch. This will take control down to where bracketed groups, + including assertions, are processed. */ - /* This is needed for all successful cases. */ + if (ptr[1] == CHAR_QUESTION_MARK && (ptr[2] == CHAR_EQUALS_SIGN || + ptr[2] == CHAR_EXCLAMATION_MARK || ptr[2] == CHAR_LESS_THAN_SIGN)) + break; - skipbytes = 3; + /* Most other conditions use OP_CREF (a couple change to OP_RREF + below), and all need to skip 3 bytes at the start of the group. */ - /* Read the name, but also get it as a number if it's all digits */ + code[1+LINK_SIZE] = OP_CREF; + skipbytes = 3; + refsign = -1; - name = ++ptr; - while (*ptr != ')') - { - if (condref >= 0) - condref = ((digitab[*ptr] & ctype_digit) != 0)? - condref * 10 + *ptr - '0' : -1; - ptr++; - } - namelen = ptr - name; + /* Check for a test for recursion in a named group. */ + + if (ptr[1] == CHAR_R && ptr[2] == CHAR_AMPERSAND) + { + terminator = -1; + ptr += 2; + code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ + } + + /* Check for a test for a named group's having been set, using the Perl + syntax (?(<name>) or (?('name') */ + + else if (ptr[1] == CHAR_LESS_THAN_SIGN) + { + terminator = CHAR_GREATER_THAN_SIGN; + ptr++; + } + else if (ptr[1] == CHAR_APOSTROPHE) + { + terminator = CHAR_APOSTROPHE; ptr++; + } + else + { + terminator = 0; + if (ptr[1] == CHAR_MINUS || ptr[1] == CHAR_PLUS) refsign = *(++ptr); + } - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } + /* We now expect to read a name; any thing else is an error */ - /* Found a previous named subpattern */ + if ((cd->ctypes[ptr[1]] & ctype_word) == 0) + { + ptr += 1; /* To get the right offset */ + *errorcodeptr = ERR28; + goto FAILED; + } - if (i < cd->names_found) - { - condref = GET2(slot, 0); - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); - } + /* Read the name, but also get it as a number if it's all digits */ - /* Search the pattern for a forward reference */ + recno = 0; + name = ++ptr; + while ((cd->ctypes[*ptr] & ctype_word) != 0) + { + if (recno >= 0) + recno = ((digitab[*ptr] & ctype_digit) != 0)? + recno * 10 + *ptr - CHAR_0 : -1; + ptr++; + } + namelen = ptr - name; - else if ((i = find_named_parens(ptr, *brackets, name, namelen)) > 0) - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, i); - } + if ((terminator > 0 && *ptr++ != terminator) || + *ptr++ != CHAR_RIGHT_PARENTHESIS) + { + ptr--; /* Error offset */ + *errorcodeptr = ERR26; + goto FAILED; + } - /* Check for 'R' for recursion */ + /* Do no further checking in the pre-compile phase. */ - else if (namelen == 1 && *name == 'R') - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, CREF_RECURSE); - } + if (lengthptr != NULL) break; - /* Check for a subpattern number */ + /* In the real compile we do the work of looking for the actual + reference. If the string started with "+" or "-" we require the rest to + be digits, in which case recno will be set. */ - else if (condref > 0) + if (refsign > 0) + { + if (recno <= 0) { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); + *errorcodeptr = ERR58; + goto FAILED; } - - /* Either an unidentified subpattern, or a reference to (?(0) */ - - else + recno = (refsign == CHAR_MINUS)? + cd->bracount - recno + 1 : recno +cd->bracount; + if (recno <= 0 || recno > cd->final_bracount) { - *errorcodeptr = (condref == 0)? ERR35: ERR15; + *errorcodeptr = ERR15; goto FAILED; } + PUT2(code, 2+LINK_SIZE, recno); + break; } - /* For conditions that are assertions, we just fall through, having - set bravalue above. */ - - break; + /* Otherwise (did not start with "+" or "-"), start by looking for the + name. */ - case '=': /* Positive lookahead */ - bravalue = OP_ASSERT; - ptr++; - break; + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) + { + if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + slot += cd->name_entry_size; + } - case '!': /* Negative lookahead */ - bravalue = OP_ASSERT_NOT; - ptr++; - break; + /* Found a previous named subpattern */ - case '<': /* Lookbehinds */ - switch (*(++ptr)) + if (i < cd->names_found) { - case '=': /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - ptr++; - break; - - case '!': /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - ptr++; - break; + recno = GET2(slot, 0); + PUT2(code, 2+LINK_SIZE, recno); } - break; - case '>': /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; + /* Search the pattern for a forward reference */ - case 'C': /* Callout - may be followed by digits; */ - previous_callout = code; /* Save for later completion */ - after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; /* Already checked that the terminating */ - { /* closing parenthesis is present. */ - int n = 0; - while ((digitab[*(++ptr)] & ctype_digit) != 0) - n = n * 10 + *ptr - '0'; - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; + else if ((i = find_parens(cd, name, namelen, + (options & PCRE_EXTENDED) != 0)) > 0) + { + PUT2(code, 2+LINK_SIZE, i); } - previous = NULL; - continue; - case 'P': /* Named subpattern handling */ - if (*(++ptr) == '<') /* Definition */ + /* If terminator == 0 it means that the name followed directly after + the opening parenthesis [e.g. (?(abc)...] and in this case there are + some further alternatives to try. For the cases where terminator != 0 + [things like (?(<name>... or (?('name')... or (?(R&name)... ] we have + now checked all the possibilities, so give an error. */ + + else if (terminator != 0) { - int i, namelen; - uschar *slot = cd->name_table; - const uschar *name; /* Don't amalgamate; some compilers */ - name = ++ptr; /* grumble at autoincrement in declaration */ + *errorcodeptr = ERR15; + goto FAILED; + } - while (*ptr++ != '>'); - namelen = ptr - name - 1; + /* Check for (?(R) for recursion. Allow digits after R to specify a + specific group number. */ - for (i = 0; i < cd->names_found; i++) + else if (*name == CHAR_R) + { + recno = 0; + for (i = 1; i < namelen; i++) + { + if ((digitab[name[i]] & ctype_digit) == 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + recno = recno * 10 + name[i] - CHAR_0; + } + if (recno == 0) recno = RREF_ANY; + code[1+LINK_SIZE] = OP_RREF; /* Change test type */ + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Similarly, check for the (?(DEFINE) "condition", which is always + false. */ + + else if (namelen == 6 && strncmp((char *)name, STRING_DEFINE, 6) == 0) + { + code[1+LINK_SIZE] = OP_DEF; + skipbytes = 1; + } + + /* Check for the "name" actually being a subpattern number. We are + in the second pass here, so final_bracount is set. */ + + else if (recno > 0 && recno <= cd->final_bracount) + { + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Either an unidentified subpattern, or a reference to (?(0) */ + + else + { + *errorcodeptr = (recno == 0)? ERR35: ERR15; + goto FAILED; + } + break; + + + /* ------------------------------------------------------------ */ + case CHAR_EQUALS_SIGN: /* Positive lookahead */ + bravalue = OP_ASSERT; + ptr++; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_EXCLAMATION_MARK: /* Negative lookahead */ + ptr++; + if (*ptr == CHAR_RIGHT_PARENTHESIS) /* Optimize (?!) */ + { + *code++ = OP_FAIL; + previous = NULL; + continue; + } + bravalue = OP_ASSERT_NOT; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_LESS_THAN_SIGN: /* Lookbehind or named define */ + switch (ptr[1]) + { + case CHAR_EQUALS_SIGN: /* Positive lookbehind */ + bravalue = OP_ASSERTBACK; + ptr += 2; + break; + + case CHAR_EXCLAMATION_MARK: /* Negative lookbehind */ + bravalue = OP_ASSERTBACK_NOT; + ptr += 2; + break; + + default: /* Could be name define, else bad */ + if ((cd->ctypes[ptr[1]] & ctype_word) != 0) goto DEFINE_NAME; + ptr++; /* Correct offset for error */ + *errorcodeptr = ERR24; + goto FAILED; + } + break; + + + /* ------------------------------------------------------------ */ + case CHAR_GREATER_THAN_SIGN: /* One-time brackets */ + bravalue = OP_ONCE; + ptr++; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_C: /* Callout - may be followed by digits; */ + previous_callout = code; /* Save for later completion */ + after_manual_callout = 1; /* Skip one item before completing */ + *code++ = OP_CALLOUT; + { + int n = 0; + while ((digitab[*(++ptr)] & ctype_digit) != 0) + n = n * 10 + *ptr - CHAR_0; + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR39; + goto FAILED; + } + if (n > 255) { - int crc = memcmp(name, slot+2, namelen); - if (crc == 0) + *errorcodeptr = ERR38; + goto FAILED; + } + *code++ = n; + PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ + PUT(code, LINK_SIZE, 0); /* Default length */ + code += 2 * LINK_SIZE; + } + previous = NULL; + continue; + + + /* ------------------------------------------------------------ */ + case CHAR_P: /* Python-style named subpattern handling */ + if (*(++ptr) == CHAR_EQUALS_SIGN || + *ptr == CHAR_GREATER_THAN_SIGN) /* Reference or recursion */ + { + is_recurse = *ptr == CHAR_GREATER_THAN_SIGN; + terminator = CHAR_RIGHT_PARENTHESIS; + goto NAMED_REF_OR_RECURSE; + } + else if (*ptr != CHAR_LESS_THAN_SIGN) /* Test for Python-style defn */ + { + *errorcodeptr = ERR41; + goto FAILED; + } + /* Fall through to handle (?P< as (?< is handled */ + + + /* ------------------------------------------------------------ */ + DEFINE_NAME: /* Come here from (?< handling */ + case CHAR_APOSTROPHE: + { + terminator = (*ptr == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; + name = ++ptr; + + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + namelen = ptr - name; + + /* In the pre-compile phase, just do a syntax check. */ + + if (lengthptr != NULL) + { + if (*ptr != terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + if (cd->names_found >= MAX_NAME_COUNT) + { + *errorcodeptr = ERR49; + goto FAILED; + } + if (namelen + 3 > cd->name_entry_size) { - if (slot[2+namelen] == 0) + cd->name_entry_size = namelen + 3; + if (namelen > MAX_NAME_SIZE) { - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } + *errorcodeptr = ERR48; + goto FAILED; } - else crc = -1; /* Current name is substring */ } - if (crc < 0) + } + + /* In the real compile, create the entry in the table */ + + else + { + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) { - memmove(slot + cd->name_entry_size, slot, - (cd->names_found - i) * cd->name_entry_size); - break; + int crc = memcmp(name, slot+2, namelen); + if (crc == 0) + { + if (slot[2+namelen] == 0) + { + if ((options & PCRE_DUPNAMES) == 0) + { + *errorcodeptr = ERR43; + goto FAILED; + } + } + else crc = -1; /* Current name is substring */ + } + if (crc < 0) + { + memmove(slot + cd->name_entry_size, slot, + (cd->names_found - i) * cd->name_entry_size); + break; + } + slot += cd->name_entry_size; } - slot += cd->name_entry_size; - } - PUT2(slot, 0, *brackets + 1); - memcpy(slot + 2, name, namelen); - slot[2+namelen] = 0; - cd->names_found++; - goto NUMBERED_GROUP; + PUT2(slot, 0, cd->bracount + 1); + memcpy(slot + 2, name, namelen); + slot[2+namelen] = 0; + } } - if (*ptr == '=' || *ptr == '>') /* Reference or recursion */ + /* In both cases, count the number of names we've encountered. */ + + ptr++; /* Move past > or ' */ + cd->names_found++; + goto NUMBERED_GROUP; + + + /* ------------------------------------------------------------ */ + case CHAR_AMPERSAND: /* Perl recursion/subroutine syntax */ + terminator = CHAR_RIGHT_PARENTHESIS; + is_recurse = TRUE; + /* Fall through */ + + /* We come here from the Python syntax above that handles both + references (?P=name) and recursion (?P>name), as well as falling + through from the Perl recursion syntax (?&name). We also come here from + the Perl \k<name> or \k'name' back reference syntax and the \k{name} + .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */ + + NAMED_REF_OR_RECURSE: + name = ++ptr; + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + namelen = ptr - name; + + /* In the pre-compile phase, do a syntax check and set a dummy + reference number. */ + + if (lengthptr != NULL) { - int i, namelen; - int type = *ptr++; - const uschar *name = ptr; - uschar *slot = cd->name_table; + if (namelen == 0) + { + *errorcodeptr = ERR62; + goto FAILED; + } + if (*ptr != terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + if (namelen > MAX_NAME_SIZE) + { + *errorcodeptr = ERR48; + goto FAILED; + } + recno = 0; + } - while (*ptr != ')') ptr++; - namelen = ptr - name; + /* In the real compile, seek the name in the table. We check the name + first, and then check that we have reached the end of the name in the + table. That way, if the name that is longer than any in the table, + the comparison will fail without reading beyond the table entry. */ + else + { + slot = cd->name_table; for (i = 0; i < cd->names_found; i++) { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + if (strncmp((char *)name, (char *)slot+2, namelen) == 0 && + slot[2+namelen] == 0) + break; slot += cd->name_entry_size; } @@ -3097,71 +4900,141 @@ recno = GET2(slot, 0); } else if ((recno = /* Forward back reference */ - find_named_parens(ptr, *brackets, name, namelen)) <= 0) + find_parens(cd, name, namelen, + (options & PCRE_EXTENDED) != 0)) <= 0) { *errorcodeptr = ERR15; goto FAILED; } + } - if (type == '>') goto HANDLE_RECURSION; /* A few lines below */ - - /* Back reference */ + /* In both phases, we can now go to the code than handles numerical + recursion or backreferences. */ - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - continue; - } + if (is_recurse) goto HANDLE_RECURSION; + else goto HANDLE_REFERENCE; - /* Should never happen */ - break; - case 'R': /* Pattern recursion */ + /* ------------------------------------------------------------ */ + case CHAR_R: /* Recursion */ ptr++; /* Same as (?0) */ /* Fall through */ - /* Recursion or "subroutine" call */ - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': + /* ------------------------------------------------------------ */ + case CHAR_MINUS: case CHAR_PLUS: /* Recursion or subroutine */ + case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: + case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: { const uschar *called; + terminator = CHAR_RIGHT_PARENTHESIS; + + /* Come here from the \g<...> and \g'...' code (Oniguruma + compatibility). However, the syntax has been checked to ensure that + the ... are a (signed) number, so that neither ERR63 nor ERR29 will + be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY + ever be taken. */ + + HANDLE_NUMERICAL_RECURSION: + + if ((refsign = *ptr) == CHAR_PLUS) + { + ptr++; + if ((digitab[*ptr] & ctype_digit) == 0) + { + *errorcodeptr = ERR63; + goto FAILED; + } + } + else if (refsign == CHAR_MINUS) + { + if ((digitab[ptr[1]] & ctype_digit) == 0) + goto OTHER_CHAR_AFTER_QUERY; + ptr++; + } + recno = 0; while((digitab[*ptr] & ctype_digit) != 0) - recno = recno * 10 + *ptr++ - '0'; + recno = recno * 10 + *ptr++ - CHAR_0; + + if (*ptr != terminator) + { + *errorcodeptr = ERR29; + goto FAILED; + } + + if (refsign == CHAR_MINUS) + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else if (refsign == CHAR_PLUS) + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno += cd->bracount; + } /* Come here from code above that handles a named recursion */ HANDLE_RECURSION: previous = code; + called = cd->start_code; - /* Find the bracket that is being referenced. Temporarily end the - regex in case it doesn't exist. */ + /* When we are actually compiling, find the bracket that is being + referenced. Temporarily end the regex in case it doesn't exist before + this point. If we end up with a forward reference, first check that + the bracket does occur later so we can give the error (and position) + now. Then remember this forward reference in the workspace so it can + be filled in at the end. */ - *code = OP_END; - called = (recno == 0)? cd->start_code : - find_bracket(cd->start_code, utf8, recno); - if (called == NULL) + if (lengthptr == NULL) { - *errorcodeptr = ERR15; - goto FAILED; - } + *code = OP_END; + if (recno != 0) called = find_bracket(cd->start_code, utf8, recno); - /* If the subpattern is still open, this is a recursive call. We - check to see if this is a left recursion that could loop for ever, - and diagnose that case. */ + /* Forward reference */ - if (GET(called, 1) == 0 && could_be_empty(called, code, bcptr, utf8)) - { - *errorcodeptr = ERR40; - goto FAILED; + if (called == NULL) + { + if (find_parens(cd, NULL, recno, + (options & PCRE_EXTENDED) != 0) < 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + called = cd->start_code + recno; + PUTINC(cd->hwm, 0, code + 2 + LINK_SIZE - cd->start_code); + } + + /* If not a forward reference, and the subpattern is still open, + this is a recursive call. We check to see if this is a left + recursion that could loop for ever, and diagnose that case. */ + + else if (GET(called, 1) == 0 && + could_be_empty(called, code, bcptr, utf8)) + { + *errorcodeptr = ERR40; + goto FAILED; + } } /* Insert the recursion/subroutine item, automatically wrapped inside - "once" brackets. */ + "once" brackets. Set up a "previous group" length so that a + subsequent quantifier will work. */ *code = OP_ONCE; PUT(code, 1, 2 + 2*LINK_SIZE); @@ -3174,28 +5047,43 @@ *code = OP_KET; PUT(code, 1, 2 + 2*LINK_SIZE); code += 1 + LINK_SIZE; + + length_prevgroup = 3 + 3*LINK_SIZE; } + + /* Can't determine a first byte now */ + + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; continue; - /* Character after (? not specially recognized */ - default: /* Option setting */ + /* ------------------------------------------------------------ */ + default: /* Other characters: check option setting */ + OTHER_CHAR_AFTER_QUERY: set = unset = 0; optset = &set; - while (*ptr != ')' && *ptr != ':') + while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON) { switch (*ptr++) { - case '-': optset = &unset; break; + case CHAR_MINUS: optset = &unset; break; - case 'i': *optset |= PCRE_CASELESS; break; - case 'J': *optset |= PCRE_DUPNAMES; break; - case 'm': *optset |= PCRE_MULTILINE; break; - case 's': *optset |= PCRE_DOTALL; break; - case 'x': *optset |= PCRE_EXTENDED; break; - case 'U': *optset |= PCRE_UNGREEDY; break; - case 'X': *optset |= PCRE_EXTRA; break; + case CHAR_J: /* Record that it changed in the external options */ + *optset |= PCRE_DUPNAMES; + cd->external_flags |= PCRE_JCHANGED; + break; + + case CHAR_i: *optset |= PCRE_CASELESS; break; + case CHAR_m: *optset |= PCRE_MULTILINE; break; + case CHAR_s: *optset |= PCRE_DOTALL; break; + case CHAR_x: *optset |= PCRE_EXTENDED; break; + case CHAR_U: *optset |= PCRE_UNGREEDY; break; + case CHAR_X: *optset |= PCRE_EXTRA; break; + + default: *errorcodeptr = ERR12; + ptr--; /* Correct the offset */ + goto FAILED; } } @@ -3204,33 +5092,52 @@ newoptions = (options | set) & (~unset); /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. Compile - code to change the ims options if this setting actually changes any of - them. We also pass the new setting back so that it can be put at the - start of any following branches, and when this group ends (if we are in - a group), a resetting item can be compiled. - - Note that if this item is right at the start of the pattern, the - options will have been abstracted and made global, so there will be no - change to compile. */ - - if (*ptr == ')') + group with option changes, so the options change at this level. If this + item is right at the start of the pattern, the options can be + abstracted and made external in the pre-compile phase, and ignored in + the compile phase. This can be helpful when matching -- for instance in + caseless checking of required bytes. + + If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are + definitely *not* at the start of the pattern because something has been + compiled. In the pre-compile phase, however, the code pointer can have + that value after the start, because it gets reset as code is discarded + during the pre-compile. However, this can happen only at top level - if + we are within parentheses, the starting BRA will still be present. At + any parenthesis level, the length value can be used to test if anything + has been compiled at that level. Thus, a test for both these conditions + is necessary to ensure we correctly detect the start of the pattern in + both phases. + + If we are not at the pattern start, compile code to change the ims + options if this setting actually changes any of them, and reset the + greedy defaults and the case value for firstbyte and reqbyte. */ + + if (*ptr == CHAR_RIGHT_PARENTHESIS) { - if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) + if (code == cd->start_code + 1 + LINK_SIZE && + (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) + { + cd->external_options = newoptions; + } + else { - *code++ = OP_OPT; - *code++ = newoptions & PCRE_IMS; + if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) + { + *code++ = OP_OPT; + *code++ = newoptions & PCRE_IMS; + } + greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); + greedy_non_default = greedy_default ^ 1; + req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; } /* Change options at this level, and pass them back for use - in subsequent branches. Reset the greedy defaults and the case - value for firstbyte and reqbyte. */ + in subsequent branches. When not at the start of the pattern, this + information is also necessary so that a resetting item can be + compiled at the end of a group (if we are in a group). */ *optionsptr = options = newoptions; - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - previous = NULL; /* This item can't be repeated */ continue; /* It is complete */ } @@ -3242,58 +5149,57 @@ bravalue = OP_BRA; ptr++; - } - } + } /* End of switch for character following (? */ + } /* End of (? handling */ - /* If PCRE_NO_AUTO_CAPTURE is set, all unadorned brackets become - non-capturing and behave like (?:...) brackets */ + /* Opening parenthesis not followed by '?'. If PCRE_NO_AUTO_CAPTURE is set, + all unadorned brackets become non-capturing and behave like (?:...) + brackets. */ else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) { bravalue = OP_BRA; } - /* Else we have a referencing group; adjust the opcode. If the bracket - number is greater than EXTRACT_BASIC_MAX, we set the opcode one higher, and - arrange for the true number to follow later, in an OP_BRANUMBER item. */ + /* Else we have a capturing group. */ else { NUMBERED_GROUP: - if (++(*brackets) > EXTRACT_BASIC_MAX) - { - bravalue = OP_BRA + EXTRACT_BASIC_MAX + 1; - code[1+LINK_SIZE] = OP_BRANUMBER; - PUT2(code, 2+LINK_SIZE, *brackets); - skipbytes = 3; - } - else bravalue = OP_BRA + *brackets; + cd->bracount += 1; + PUT2(code, 1+LINK_SIZE, cd->bracount); + skipbytes = 2; } - /* Process nested bracketed re. Assertions may not be repeated, but other - kinds can be. We copy code into a non-register variable in order to be able - to pass its address because some compilers complain otherwise. Pass in a - new setting for the ims options if they have changed. */ + /* Process nested bracketed regex. Assertions may not be repeated, but + other kinds can be. All their opcodes are >= OP_ONCE. We copy code into a + non-register variable in order to be able to pass its address because some + compilers complain otherwise. Pass in a new setting for the ims options if + they have changed. */ previous = (bravalue >= OP_ONCE)? code : NULL; *code = bravalue; tempcode = code; tempreqvary = cd->req_varyopt; /* Save value before bracket */ + length_prevgroup = 0; /* Initialize for pre-compile phase */ if (!compile_regex( newoptions, /* The complete new option state */ options & PCRE_IMS, /* The previous ims option state */ - brackets, /* Extracting bracket count */ &tempcode, /* Where to put code (updated) */ &ptr, /* Input pointer (updated) */ errorcodeptr, /* Where to put an error message */ (bravalue == OP_ASSERTBACK || bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - skipbytes, /* Skip over OP_COND/OP_BRANUMBER */ + reset_bracount, /* True if (?| group */ + skipbytes, /* Skip over bracket number */ &subfirstbyte, /* For possible first char */ &subreqbyte, /* For possible last char */ bcptr, /* Current branch chain */ - cd)) /* Tables block */ + cd, /* Tables block */ + (lengthptr == NULL)? NULL : /* Actual compile phase */ + &length_prevgroup /* Pre-compile phase */ + )) goto FAILED; /* At the end of compiling, code is still pointing to the start of the @@ -3302,9 +5208,11 @@ is on the bracket. */ /* If this is a conditional bracket, check that there are no more than - two branches in the group. */ + two branches in the group, or just one if it's a DEFINE group. We do this + in the real compile phase, not in the pre-pass, where the whole group may + not be available. */ - else if (bravalue == OP_COND) + if (bravalue == OP_COND && lengthptr == NULL) { uschar *tc = code; int condcount = 0; @@ -3315,29 +5223,83 @@ } while (*tc != OP_KET); - if (condcount > 2) + /* A DEFINE group is never obeyed inline (the "condition" is always + false). It must have only one branch. */ + + if (code[LINK_SIZE+1] == OP_DEF) { - *errorcodeptr = ERR27; - goto FAILED; + if (condcount > 1) + { + *errorcodeptr = ERR54; + goto FAILED; + } + bravalue = OP_DEF; /* Just a flag to suppress char handling below */ + } + + /* A "normal" conditional group. If there is just one branch, we must not + make use of its firstbyte or reqbyte, because this is equivalent to an + empty second branch. */ + + else + { + if (condcount > 2) + { + *errorcodeptr = ERR27; + goto FAILED; + } + if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; } + } + + /* Error if hit end of pattern */ + + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR14; + goto FAILED; + } - /* If there is just one branch, we must not make use of its firstbyte or - reqbyte, because this is equivalent to an empty second branch. */ + /* In the pre-compile phase, update the length by the length of the group, + less the brackets at either end. Then reduce the compiled code to just a + set of non-capturing brackets so that it doesn't use much memory if it is + duplicated by a quantifier.*/ - if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; + *code++ = OP_BRA; + PUTINC(code, 0, 1 + LINK_SIZE); + *code++ = OP_KET; + PUTINC(code, 0, 1 + LINK_SIZE); + break; /* No need to waste time with special character handling */ } - /* Handle updating of the required and first characters. Update for normal - brackets of all kinds, and conditions with two branches (see code above). - If the bracket is followed by a quantifier with zero repeat, we have to - back off. Hence the definition of zeroreqbyte and zerofirstbyte outside the - main loop so that they can be accessed for the back off. */ + /* Otherwise update the main code pointer to the end of the group. */ + + code = tempcode; + + /* For a DEFINE group, required and first character settings are not + relevant. */ + + if (bravalue == OP_DEF) break; + + /* Handle updating of the required and first characters for other types of + group. Update for normal brackets of all kinds, and conditions with two + branches (see code above). If the bracket is followed by a quantifier with + zero repeat, we have to back off. Hence the definition of zeroreqbyte and + zerofirstbyte outside the main loop so that they can be accessed for the + back off. */ zeroreqbyte = reqbyte; zerofirstbyte = firstbyte; groupsetfirstbyte = FALSE; - if (bravalue >= OP_BRA || bravalue == OP_ONCE || bravalue == OP_COND) + if (bravalue >= OP_ONCE) { /* If we have not yet set a firstbyte in this branch, take it from the subpattern, remembering that it was set here so that a repeat of more @@ -3378,44 +5340,34 @@ firstbyte, looking for an asserted first char. */ else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; + break; /* End of processing '(' */ - /* Now update the main code pointer to the end of the group. */ - - code = tempcode; - - /* Error if hit end of pattern */ - - if (*ptr != ')') - { - *errorcodeptr = ERR14; - goto FAILED; - } - break; - - /* Check \ for being a real metacharacter; if not, fall through and handle - it as a data character at the start of a string. Escape items are checked - for validity in the pre-compiling pass. */ - - case '\\': - tempptr = ptr; - c = check_escape(&ptr, errorcodeptr, *brackets, options, FALSE); - /* Handle metacharacters introduced by \. For ones like \d, the ESC_ values + /* ===================================================================*/ + /* Handle metasequences introduced by \. For ones like \d, the ESC_ values are arranged to be the negation of the corresponding OP_values. For the back references, the values are ESC_REF plus the reference number. Only back references and those types that consume a character may be repeated. We can test for values between ESC_b and ESC_Z for the latter; this may have to change if any new ones are ever created. */ + case CHAR_BACKSLASH: + tempptr = ptr; + c = check_escape(&ptr, errorcodeptr, cd->bracount, options, FALSE); + if (*errorcodeptr != 0) goto FAILED; + if (c < 0) { if (-c == ESC_Q) /* Handle start of quoted string */ { - if (ptr[1] == '\\' && ptr[2] == 'E') ptr += 2; /* avoid empty string */ - else inescq = TRUE; + if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) + ptr += 2; /* avoid empty string */ + else inescq = TRUE; continue; } + if (-c == ESC_E) continue; /* Perl ignores an orphan \E */ + /* For metasequences that actually match a character, we disable the setting of a first character if it hasn't already been set. */ @@ -3427,18 +5379,96 @@ zerofirstbyte = firstbyte; zeroreqbyte = reqbyte; - /* Back references are handled specially */ + /* \g<name> or \g'name' is a subroutine call by name and \g<n> or \g'n' + is a subroutine call by number (Oniguruma syntax). In fact, the value + -ESC_g is returned only for these cases. So we don't need to check for < + or ' if the value is -ESC_g. For the Perl syntax \g{n} the value is + -ESC_REF+n, and for the Perl syntax \g{name} the result is -ESC_k (as + that is a synonym for a named back reference). */ - if (-c >= ESC_REF) + if (-c == ESC_g) { - int number = -c - ESC_REF; - previous = code; + const uschar *p; + save_hwm = cd->hwm; /* Normally this is set when '(' is read */ + terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; + + /* These two statements stop the compiler for warning about possibly + unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In + fact, because we actually check for a number below, the paths that + would actually be in error are never taken. */ + + skipbytes = 0; + reset_bracount = FALSE; + + /* Test for a name */ + + if (ptr[1] != CHAR_PLUS && ptr[1] != CHAR_MINUS) + { + BOOL isnumber = TRUE; + for (p = ptr + 1; *p != 0 && *p != terminator; p++) + { + if ((cd->ctypes[*p] & ctype_digit) == 0) isnumber = FALSE; + if ((cd->ctypes[*p] & ctype_word) == 0) break; + } + if (*p != terminator) + { + *errorcodeptr = ERR57; + break; + } + if (isnumber) + { + ptr++; + goto HANDLE_NUMERICAL_RECURSION; + } + is_recurse = TRUE; + goto NAMED_REF_OR_RECURSE; + } + + /* Test a signed number in angle brackets or quotes. */ + + p = ptr + 2; + while ((digitab[*p] & ctype_digit) != 0) p++; + if (*p != terminator) + { + *errorcodeptr = ERR57; + break; + } + ptr++; + goto HANDLE_NUMERICAL_RECURSION; + } + + /* \k<name> or \k'name' is a back reference by name (Perl syntax). + We also support \k{name} (.NET syntax) */ + + if (-c == ESC_k && (ptr[1] == CHAR_LESS_THAN_SIGN || + ptr[1] == CHAR_APOSTROPHE || ptr[1] == CHAR_LEFT_CURLY_BRACKET)) + { + is_recurse = FALSE; + terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)? + CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET; + goto NAMED_REF_OR_RECURSE; + } + + /* Back references are handled specially; must disable firstbyte if + not set to cope with cases like (?=(\w+))\1: which would otherwise set + ':' later. */ + + if (-c >= ESC_REF) + { + recno = -c - ESC_REF; + + HANDLE_REFERENCE: /* Come here from named backref handling */ + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + previous = code; *code++ = OP_REF; - PUT2INC(code, 0, number); + PUT2INC(code, 0, recno); + cd->backref_map |= (recno < 32)? (1 << recno) : 1; + if (recno > cd->top_backref) cd->top_backref = recno; } - /* So are Unicode property matches, if supported. We know that get_ucp - won't fail because it was tested in the pre-pass. */ + /* So are Unicode property matches, if supported. */ #ifdef SUPPORT_UCP else if (-c == ESC_P || -c == ESC_p) @@ -3446,15 +5476,26 @@ BOOL negated; int pdata; int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + if (ptype < 0) goto FAILED; previous = code; *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; *code++ = ptype; *code++ = pdata; } +#else + + /* If Unicode properties are not supported, \X, \P, and \p are not + allowed. */ + + else if (-c == ESC_X || -c == ESC_P || -c == ESC_p) + { + *errorcodeptr = ERR45; + goto FAILED; + } #endif - /* For the rest, we can obtain the OP value by negating the escape - value */ + /* For the rest (including \X when Unicode properties are supported), we + can obtain the OP value by negating the escape value. */ else { @@ -3478,9 +5519,10 @@ mcbuffer[0] = c; mclength = 1; } - goto ONE_CHAR; + + /* ===================================================================*/ /* Handle a literal character. It is guaranteed not to be whitespace or # when the extended flag is set. If we are in UTF-8 mode, it may be a multi-byte literal character. */ @@ -3491,7 +5533,7 @@ mcbuffer[0] = c; #ifdef SUPPORT_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) + if (utf8 && c >= 0xc0) { while ((ptr[1] & 0xc0) == 0x80) mcbuffer[mclength++] = *(++ptr); @@ -3506,6 +5548,11 @@ *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARNC : OP_CHAR; for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; + /* Remember if \r or \n were seen */ + + if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL) + cd->external_flags |= PCRE_HASCRORLF; + /* Set the first and required bytes appropriately. If no previous first byte, set it from this character, but revert to none on a zero repeat. Otherwise, leave the firstbyte value alone, and don't change it on a zero @@ -3542,6 +5589,7 @@ } } /* end of big loop */ + /* Control never reaches here by falling through, only by a goto for all the error states. Pass back the position in the pattern so that it can be displayed to the user for diagnosing the error. */ @@ -3558,35 +5606,42 @@ * Compile sequence of alternatives * *************************************************/ -/* On entry, ptr is pointing past the bracket character, but on return -it points to the closing bracket, or vertical bar, or end of string. -The code variable is pointing at the byte into which the BRA operator has been -stored. If the ims options are changed at the start (for a (?ims: group) or -during any branch, we need to insert an OP_OPT item at the start of every -following branch to ensure they get set correctly at run time, and also pass -the new options into every subsequent branch compile. +/* On entry, ptr is pointing past the bracket character, but on return it +points to the closing bracket, or vertical bar, or end of string. The code +variable is pointing at the byte into which the BRA operator has been stored. +If the ims options are changed at the start (for a (?ims: group) or during any +branch, we need to insert an OP_OPT item at the start of every following branch +to ensure they get set correctly at run time, and also pass the new options +into every subsequent branch compile. + +This function is used during the pre-compile phase when we are trying to find +out the amount of memory needed, as well as during the real compile phase. The +value of lengthptr distinguishes the two phases. -Argument: +Arguments: options option bits, including any changes for this subpattern oldims previous settings of ims option bits - brackets -> int containing the number of extracting brackets used codeptr -> the address of the current code pointer ptrptr -> the address of the current pattern pointer errorcodeptr -> pointer to error code variable lookbehind TRUE if this is a lookbehind assertion - skipbytes skip this many bytes at start (for OP_COND, OP_BRANUMBER) + reset_bracount TRUE to reset the count for each branch + skipbytes skip this many bytes at start (for brackets and OP_COND) firstbyteptr place to put the first required character, or a negative number reqbyteptr place to put the last required character, or a negative number bcptr pointer to the chain of currently open branches cd points to the data block with tables pointers etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase -Returns: TRUE on success +Returns: TRUE on success */ static BOOL -compile_regex(int options, int oldims, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, BOOL lookbehind, int skipbytes, - int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr, + int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, + int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd, + int *lengthptr) { const uschar *ptr = *ptrptr; uschar *code = *codeptr; @@ -3595,6 +5650,9 @@ uschar *reverse_count = NULL; int firstbyte, reqbyte; int branchfirstbyte, branchreqbyte; +int length; +int orig_bracount; +int max_bracount; branch_chain bc; bc.outer = bcptr; @@ -3602,6 +5660,20 @@ firstbyte = reqbyte = REQ_UNSET; +/* Accumulate the length for use in the pre-compile phase. Start with the +length of the BRA and KET and any extra bytes that are required at the +beginning. We accumulate in a local variable to save frequent testing of +lenthptr for NULL. We cannot do this by looking at the value of code at the +start and end of each alternative, because compiled items are discarded during +the pre-compile phase so that the work space is not exceeded. */ + +length = 2 + 2*LINK_SIZE + skipbytes; + +/* WARNING: If the above line is changed for any reason, you must also change +the code that abstracts option settings at the start of the pattern and makes +them global. It tests the value of length for (2 + 2*LINK_SIZE) in the +pre-compile phase to find out whether anything has yet been compiled or not. */ + /* Offset is set zero to mark that this bracket is still open */ PUT(code, 1, 0); @@ -3609,14 +5681,21 @@ /* Loop for each alternative branch */ +orig_bracount = max_bracount = cd->bracount; for (;;) { + /* For a (?| group, reset the capturing bracket count so that each branch + uses the same numbers. */ + + if (reset_bracount) cd->bracount = orig_bracount; + /* Handle a change of ims options at the start of the branch */ if ((options & PCRE_IMS) != oldims) { *code++ = OP_OPT; *code++ = options & PCRE_IMS; + length += 2; } /* Set up dummy OP_REVERSE if lookbehind assertion */ @@ -3626,95 +5705,110 @@ *code++ = OP_REVERSE; reverse_count = code; PUTINC(code, 0, 0); + length += 1 + LINK_SIZE; } - /* Now compile the branch */ + /* Now compile the branch; in the pre-compile phase its length gets added + into the length. */ - if (!compile_branch(&options, brackets, &code, &ptr, errorcodeptr, - &branchfirstbyte, &branchreqbyte, &bc, cd)) + if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstbyte, + &branchreqbyte, &bc, cd, (lengthptr == NULL)? NULL : &length)) { *ptrptr = ptr; return FALSE; } - /* If this is the first branch, the firstbyte and reqbyte values for the - branch become the values for the regex. */ + /* Keep the highest bracket count in case (?| was used and some branch + has fewer than the rest. */ - if (*last_branch != OP_ALT) - { - firstbyte = branchfirstbyte; - reqbyte = branchreqbyte; - } + if (cd->bracount > max_bracount) max_bracount = cd->bracount; - /* If this is not the first branch, the first char and reqbyte have to - match the values from all the previous branches, except that if the previous - value for reqbyte didn't have REQ_VARY set, it can still match, and we set - REQ_VARY for the regex. */ + /* In the real compile phase, there is some post-processing to be done. */ - else + if (lengthptr == NULL) { - /* If we previously had a firstbyte, but it doesn't match the new branch, - we have to abandon the firstbyte for the regex, but if there was previously - no reqbyte, it takes on the value of the old firstbyte. */ + /* If this is the first branch, the firstbyte and reqbyte values for the + branch become the values for the regex. */ - if (firstbyte >= 0 && firstbyte != branchfirstbyte) + if (*last_branch != OP_ALT) { - if (reqbyte < 0) reqbyte = firstbyte; - firstbyte = REQ_NONE; + firstbyte = branchfirstbyte; + reqbyte = branchreqbyte; } - /* If we (now or from before) have no firstbyte, a firstbyte from the - branch becomes a reqbyte if there isn't a branch reqbyte. */ + /* If this is not the first branch, the first char and reqbyte have to + match the values from all the previous branches, except that if the + previous value for reqbyte didn't have REQ_VARY set, it can still match, + and we set REQ_VARY for the regex. */ + + else + { + /* If we previously had a firstbyte, but it doesn't match the new branch, + we have to abandon the firstbyte for the regex, but if there was + previously no reqbyte, it takes on the value of the old firstbyte. */ + + if (firstbyte >= 0 && firstbyte != branchfirstbyte) + { + if (reqbyte < 0) reqbyte = firstbyte; + firstbyte = REQ_NONE; + } - if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) - branchreqbyte = branchfirstbyte; + /* If we (now or from before) have no firstbyte, a firstbyte from the + branch becomes a reqbyte if there isn't a branch reqbyte. */ - /* Now ensure that the reqbytes match */ + if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) + branchreqbyte = branchfirstbyte; - if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) - reqbyte = REQ_NONE; - else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ - } + /* Now ensure that the reqbytes match */ - /* If lookbehind, check that this branch matches a fixed-length string, - and put the length into the OP_REVERSE item. Temporarily mark the end of - the branch with OP_END. */ + if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) + reqbyte = REQ_NONE; + else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ + } - if (lookbehind) - { - int length; - *code = OP_END; - length = find_fixedlength(last_branch, options); - DPRINTF(("fixed length = %d\n", length)); - if (length < 0) + /* If lookbehind, check that this branch matches a fixed-length string, and + put the length into the OP_REVERSE item. Temporarily mark the end of the + branch with OP_END. */ + + if (lookbehind) { - *errorcodeptr = (length == -2)? ERR36 : ERR25; - *ptrptr = ptr; - return FALSE; + int fixed_length; + *code = OP_END; + fixed_length = find_fixedlength(last_branch, options); + DPRINTF(("fixed length = %d\n", fixed_length)); + if (fixed_length < 0) + { + *errorcodeptr = (fixed_length == -2)? ERR36 : ERR25; + *ptrptr = ptr; + return FALSE; + } + PUT(reverse_count, 0, fixed_length); } - PUT(reverse_count, 0, length); } - /* Reached end of expression, either ')' or end of pattern. Go back through - the alternative branches and reverse the chain of offsets, with the field in - the BRA item now becoming an offset to the first alternative. If there are - no alternatives, it points to the end of the group. The length in the - terminating ket is always the length of the whole bracketed item. If any of - the ims options were changed inside the group, compile a resetting op-code - following, except at the very end of the pattern. Return leaving the pointer - at the terminating char. */ + /* Reached end of expression, either ')' or end of pattern. In the real + compile phase, go back through the alternative branches and reverse the chain + of offsets, with the field in the BRA item now becoming an offset to the + first alternative. If there are no alternatives, it points to the end of the + group. The length in the terminating ket is always the length of the whole + bracketed item. If any of the ims options were changed inside the group, + compile a resetting op-code following, except at the very end of the pattern. + Return leaving the pointer at the terminating char. */ - if (*ptr != '|') + if (*ptr != CHAR_VERTICAL_LINE) { - int length = code - last_branch; - do + if (lengthptr == NULL) { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, length); - length = prev_length; - last_branch -= length; + int branch_length = code - last_branch; + do + { + int prev_length = GET(last_branch, 1); + PUT(last_branch, 1, branch_length); + branch_length = prev_length; + last_branch -= branch_length; + } + while (branch_length > 0); } - while (length > 0); /* Fill in the ket */ @@ -3724,30 +5818,57 @@ /* Resetting option if needed */ - if ((options & PCRE_IMS) != oldims && *ptr == ')') + if ((options & PCRE_IMS) != oldims && *ptr == CHAR_RIGHT_PARENTHESIS) { *code++ = OP_OPT; *code++ = oldims; + length += 2; } + /* Retain the highest bracket number, in case resetting was used. */ + + cd->bracount = max_bracount; + /* Set values to pass back */ *codeptr = code; *ptrptr = ptr; *firstbyteptr = firstbyte; *reqbyteptr = reqbyte; + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < length) + { + *errorcodeptr = ERR20; + return FALSE; + } + *lengthptr += length; + } return TRUE; } - /* Another branch follows; insert an "or" node. Its length field points back + /* Another branch follows. In the pre-compile phase, we can move the code + pointer back to where it was for the start of the first branch. (That is, + pretend that each branch is the only one.) + + In the real compile phase, insert an ALT node. Its length field points back to the previous branch while the bracket remains open. At the end the chain is reversed. It's done like this so that the start of the bracket has a zero offset until it is closed, making it possible to detect recursion. */ - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = last_branch = code; - code += 1 + LINK_SIZE; + if (lengthptr != NULL) + { + code = *codeptr + 1 + LINK_SIZE + skipbytes; + length += 1 + LINK_SIZE; + } + else + { + *code = OP_ALT; + PUT(code, 1, code - last_branch); + bc.current = last_branch = code; + code += 1 + LINK_SIZE; + } + ptr++; } /* Control never reaches here */ @@ -3799,35 +5920,41 @@ unsigned int backref_map) { do { - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_MULTILINE, FALSE); + const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], + options, PCRE_MULTILINE, FALSE); register int op = *scode; + /* Non-capturing brackets */ + + if (op == OP_BRA) + { + if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; + } + /* Capturing brackets */ - if (op > OP_BRA) + else if (op == OP_CBRA) { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; } /* Other brackets */ - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) + else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) { if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; } - /* .* is not anchored unless DOTALL is set and it isn't in brackets that - are or may be referenced. */ + /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and + it isn't in brackets that are or may be referenced. */ - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR) && - (*options & PCRE_DOTALL) != 0) + else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || + op == OP_TYPEPOSSTAR)) { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; + if (scode[1] != OP_ALLANY || (bracket_map & backref_map) != 0) + return FALSE; } /* Check for explicit anchoring */ @@ -3869,30 +5996,63 @@ unsigned int backref_map) { do { - const uschar *scode = first_significant_code(code + 1+LINK_SIZE, NULL, 0, - FALSE); + const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], + NULL, 0, FALSE); register int op = *scode; + /* If we are at the start of a conditional assertion group, *both* the + conditional assertion *and* what follows the condition must satisfy the test + for start of line. Other kinds of condition fail. Note that there may be an + auto-callout at the start of a condition. */ + + if (op == OP_COND) + { + scode += 1 + LINK_SIZE; + if (*scode == OP_CALLOUT) scode += _pcre_OP_lengths[OP_CALLOUT]; + switch (*scode) + { + case OP_CREF: + case OP_RREF: + case OP_DEF: + return FALSE; + + default: /* Assertion */ + if (!is_startline(scode, bracket_map, backref_map)) return FALSE; + do scode += GET(scode, 1); while (*scode == OP_ALT); + scode += 1 + LINK_SIZE; + break; + } + scode = first_significant_code(scode, NULL, 0, FALSE); + op = *scode; + } + + /* Non-capturing brackets */ + + if (op == OP_BRA) + { + if (!is_startline(scode, bracket_map, backref_map)) return FALSE; + } + /* Capturing brackets */ - if (op > OP_BRA) + else if (op == OP_CBRA) { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); if (!is_startline(scode, new_map, backref_map)) return FALSE; } /* Other brackets */ - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { if (!is_startline(scode, bracket_map, backref_map)) return FALSE; } + else if (op == OP_ASSERT || op == OP_ONCE) + { + if (!is_startline(scode, bracket_map, backref_map)) return FALSE; + } /* .* means "start at start or after \n" if it isn't in brackets that may be referenced. */ - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR) + else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) { if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; } @@ -3941,14 +6101,13 @@ first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); register int op = *scode; - if (op >= OP_BRA) op = OP_BRA; - switch(op) { default: return -1; case OP_BRA: + case OP_CBRA: case OP_ASSERT: case OP_ONCE: case OP_COND: @@ -3964,6 +6123,7 @@ case OP_CHARNC: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: if (!inassert) return -1; if (c < 0) { @@ -4004,7 +6164,7 @@ with errorptr and erroroffset set */ -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION pcre_compile(const char *pattern, int options, const char **errorptr, int *erroroffset, const unsigned char *tables) { @@ -4012,37 +6172,36 @@ } - -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION pcre_compile2(const char *pattern, int options, int *errorcodeptr, const char **errorptr, int *erroroffset, const unsigned char *tables) { real_pcre *re; -int length = 1 + LINK_SIZE; /* For initial BRA plus length */ -int c, firstbyte, reqbyte, newline; -int bracount = 0; -int branch_extra = 0; -int branch_newextra; -int item_count = -1; -int name_count = 0; -int max_name_size = 0; -int lastitemlength = 0; +int length = 1; /* For final END opcode */ +int firstbyte, reqbyte, newline; int errorcode = 0; +int skipatstart = 0; #ifdef SUPPORT_UTF8 BOOL utf8; -BOOL class_utf8; #endif -BOOL inescq = FALSE; -BOOL capturing; -unsigned int brastackptr = 0; size_t size; uschar *code; const uschar *codestart; const uschar *ptr; compile_data compile_block; compile_data *cd = &compile_block; -int brastack[BRASTACK_SIZE]; -uschar bralenstack[BRASTACK_SIZE]; + +/* This space is used for "compiling" into during the first phase, when we are +computing the amount of memory that is needed. Compiled items are thrown away +as soon as possible, so that a fairly large buffer should be sufficient for +this purpose. The same space is used in the second phase for remembering where +to fill in forward references to subpatterns. */ + +uschar cworkspace[COMPILE_WORK_SIZE]; + +/* Set this early so that early errors get offset 0. */ + +ptr = (const uschar *)pattern; /* We can't pass back an error message if errorptr is NULL; I guess the best we can do is just return NULL, but we can set a code value if there is a code @@ -4062,11 +6221,62 @@ if (erroroffset == NULL) { errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } *erroroffset = 0; +/* Set up pointers to the individual character tables */ + +if (tables == NULL) tables = _pcre_default_tables; +cd->lcc = tables + lcc_offset; +cd->fcc = tables + fcc_offset; +cd->cbits = tables + cbits_offset; +cd->ctypes = tables + ctypes_offset; + +/* Check that all undefined public option bits are zero */ + +if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0) + { + errorcode = ERR17; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Check for global one-time settings at the start of the pattern, and remember +the offset for later. */ + +while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && + ptr[skipatstart+1] == CHAR_ASTERISK) + { + int newnl = 0; + int newbsr = 0; + + if (strncmp((char *)(ptr+skipatstart+2), STRING_UTF8_RIGHTPAR, 5) == 0) + { skipatstart += 7; options |= PCRE_UTF8; continue; } + + if (strncmp((char *)(ptr+skipatstart+2), STRING_CR_RIGHTPAR, 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_LF_RIGHTPAR, 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_CRLF_RIGHTPAR, 5) == 0) + { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_ANY_RIGHTPAR, 4) == 0) + { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_ANYCRLF_RIGHTPAR, 8) == 0) + { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } + + else if (strncmp((char *)(ptr+skipatstart+2), STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_BSR_UNICODE_RIGHTPAR, 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } + + if (newnl != 0) + options = (options & ~PCRE_NEWLINE_BITS) | newnl; + else if (newbsr != 0) + options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; + else break; + } + /* Can't support UTF8 unless PCRE has been compiled to include the code. */ #ifdef SUPPORT_UTF8 @@ -4075,7 +6285,7 @@ (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) { errorcode = ERR44; - goto PCRE_EARLY_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } #else if ((options & PCRE_UTF8) != 0) @@ -4085,48 +6295,60 @@ } #endif -if ((options & ~PUBLIC_OPTIONS) != 0) +/* Check validity of \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; + case 0: + case PCRE_BSR_ANYCRLF: + case PCRE_BSR_UNICODE: + break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = _pcre_default_tables; -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Handle different types of newline. The two bits give four cases. The current -code allows for one- or two-byte sequences. */ +/* Handle different types of newline. The three bits give seven cases. The +current code allows for fixed one- or two-byte sequences, plus "any" and +"anycrlf". */ -switch (options & PCRE_NEWLINE_CRLF) +switch (options & PCRE_NEWLINE_BITS) { - default: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; + case 0: newline = NEWLINE; break; /* Build-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } -if (newline > 255) +if (newline == -2) + { + cd->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; + cd->nltype = NLTYPE_ANY; } else { - cd->nllen = 1; - cd->nl[0] = newline; + cd->nltype = NLTYPE_FIXED; + if (newline > 255) + { + cd->nllen = 2; + cd->nl[0] = (newline >> 8) & 255; + cd->nl[1] = newline & 255; + } + else + { + cd->nllen = 1; + cd->nl[0] = newline; + } } -/* Maximum back reference and backref bitmap. This is updated for numeric -references during the first pass, but for named references during the actual -compile pass. The bitmap records up to 31 back references to help in deciding -whether (.*) can be treated as anchored or not. */ +/* Maximum back reference and backref bitmap. The bitmap records up to 31 back +references to help in deciding whether (.*) can be treated as anchored or not. +*/ cd->top_backref = 0; cd->backref_map = 0; @@ -4136,1059 +6358,173 @@ DPRINTF(("------------------------------------------------------------------\n")); DPRINTF(("%s\n", pattern)); -/* The first thing to do is to make a pass over the pattern to compute the -amount of store required to hold the compiled code. This does not have to be -perfect as long as errors are overestimates. At the same time we can detect any -flag settings right at the start, and extract them. Make an attempt to correct -for any counted white space if an "extended" flag setting appears late in the -pattern. We can't be so clever for #-comments. */ - -ptr = (const uschar *)(pattern - 1); -while ((c = *(++ptr)) != 0) - { - int min, max; - int class_optcount; - int bracket_length; - int duplength; +/* Pretend to compile the pattern while actually just accumulating the length +of memory required. This behaviour is triggered by passing a non-NULL final +argument to compile_regex(). We pass a block of workspace (cworkspace) for it +to compile parts of the pattern into; the compiled code is discarded when it is +no longer needed, so hopefully this workspace will never overflow, though there +is a test for its doing so. */ - /* If we are inside a \Q...\E sequence, all chars are literal */ +cd->bracount = cd->final_bracount = 0; +cd->names_found = 0; +cd->name_entry_size = 0; +cd->name_table = NULL; +cd->start_workspace = cworkspace; +cd->start_code = cworkspace; +cd->hwm = cworkspace; +cd->start_pattern = (const uschar *)pattern; +cd->end_pattern = (const uschar *)(pattern + strlen(pattern)); +cd->req_varyopt = 0; +cd->external_options = options; +cd->external_flags = 0; - if (inescq) - { - if ((options & PCRE_AUTO_CALLOUT) != 0) length += 2 + 2*LINK_SIZE; - goto NORMAL_CHAR; - } +/* Now do the pre-compile. On error, errorcode will be set non-zero, so we +don't need to look at the result of the function here. The initial options have +been put into the cd block so that they can be changed if an option setting is +found within the regex right at the beginning. Bringing initial option settings +outside can help speed up starting point checks. */ - /* Otherwise, first check for ignored whitespace and comments */ +ptr += skipatstart; +code = cworkspace; +*code = OP_BRA; +(void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS, + &code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, + &length); +if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) - { - ptr += cd->nllen - 1; - continue; - } - break; /* End loop at end of pattern */ - } - } +DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, + cd->hwm - cworkspace)); - item_count++; /* Is zero for the first non-comment item */ +if (length > MAX_PATTERN_SIZE) + { + errorcode = ERR20; + goto PCRE_EARLY_ERROR_RETURN; + } - /* Allow space for auto callout before every item except quantifiers. */ +/* Compute the size of data block needed and get it, either from malloc or +externally provided function. Integer overflow should no longer be possible +because nowadays we limit the maximum value of cd->names_found and +cd->name_entry_size. */ - if ((options & PCRE_AUTO_CALLOUT) != 0 && - c != '*' && c != '+' && c != '?' && - (c != '{' || !is_counted_repeat(ptr + 1))) - length += 2 + 2*LINK_SIZE; +size = length + sizeof(real_pcre) + cd->names_found * (cd->name_entry_size + 3); +re = (real_pcre *)(pcre_malloc)(size); - switch(c) - { - /* A backslashed item may be an escaped data character or it may be a - character type. */ +if (re == NULL) + { + errorcode = ERR21; + goto PCRE_EARLY_ERROR_RETURN; + } - case '\\': - c = check_escape(&ptr, &errorcode, bracount, options, FALSE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; +/* Put in the magic number, and save the sizes, initial options, internal +flags, and character table pointer. NULL is used for the default character +tables. The nullpad field is at the end; it's there to help in the case when a +regex compiled on a system with 4-byte pointers is run on another with 8-byte +pointers. */ - lastitemlength = 1; /* Default length of last item for repeats */ +re->magic_number = MAGIC_NUMBER; +re->size = size; +re->options = cd->external_options; +re->flags = cd->external_flags; +re->dummy1 = 0; +re->first_byte = 0; +re->req_byte = 0; +re->name_table_offset = sizeof(real_pcre); +re->name_entry_size = cd->name_entry_size; +re->name_count = cd->names_found; +re->ref_count = 0; +re->tables = (tables == _pcre_default_tables)? NULL : tables; +re->nullpad = NULL; - if (c >= 0) /* Data character */ - { - length += 2; /* For a one-byte character */ +/* The starting points of the name/number translation table and of the code are +passed around in the compile data block. The start/end pattern and initial +options are already set from the pre-compile phase, as is the name_entry_size +field. Reset the bracket count and the names_found field. Also reset the hwm +field; this time it's used for remembering forward references to subpatterns. +*/ -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { - int i; - for (i = 0; i < _pcre_utf8_table1_size; i++) - if (c <= _pcre_utf8_table1[i]) break; - length += i; - lastitemlength += i; - } -#endif +cd->final_bracount = cd->bracount; /* Save for checking forward references */ +cd->bracount = 0; +cd->names_found = 0; +cd->name_table = (uschar *)re + re->name_table_offset; +codestart = cd->name_table + re->name_entry_size * re->name_count; +cd->start_code = codestart; +cd->hwm = cworkspace; +cd->req_varyopt = 0; +cd->had_accept = FALSE; - continue; - } +/* Set up a starting, non-extracting bracket, then compile the expression. On +error, errorcode will be set non-zero, so we don't need to look at the result +of the function here. */ - /* If \Q, enter "literal" mode */ +ptr = (const uschar *)pattern + skipatstart; +code = (uschar *)codestart; +*code = OP_BRA; +(void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr, + &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); +re->top_bracket = cd->bracount; +re->top_backref = cd->top_backref; +re->flags = cd->external_flags; - if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } +if (cd->had_accept) reqbyte = -1; /* Must disable after (*ACCEPT) */ - /* \X is supported only if Unicode property support is compiled */ +/* If not reached end of pattern on success, there's an excess bracket. */ -#ifndef SUPPORT_UCP - if (-c == ESC_X) - { - errorcode = ERR45; - goto PCRE_ERROR_RETURN; - } -#endif +if (errorcode == 0 && *ptr != 0) errorcode = ERR22; - /* \P and \p are for Unicode properties, but only when the support has - been compiled. Each item needs 3 bytes. */ +/* Fill in the terminating state and check for disastrous overflow, but +if debugging, leave the test till after things are printed out. */ - else if (-c == ESC_P || -c == ESC_p) - { -#ifdef SUPPORT_UCP - BOOL negated; - BOOL pdata; - length += 3; - lastitemlength = 3; - if (get_ucp(&ptr, &negated, &pdata, &errorcode) < 0) - goto PCRE_ERROR_RETURN; - continue; -#else - errorcode = ERR45; - goto PCRE_ERROR_RETURN; +*code++ = OP_END; + +#ifndef PCRE_DEBUG +if (code - codestart > length) errorcode = ERR23; #endif - } - /* Other escapes need one byte */ +/* Fill in any forward references that are required. */ - length++; +while (errorcode == 0 && cd->hwm > cworkspace) + { + int offset, recno; + const uschar *groupptr; + cd->hwm -= LINK_SIZE; + offset = GET(cd->hwm, 0); + recno = GET(codestart, offset); + groupptr = find_bracket(codestart, (re->options & PCRE_UTF8) != 0, recno); + if (groupptr == NULL) errorcode = ERR53; + else PUT(((uschar *)codestart), offset, groupptr - codestart); + } - /* A back reference needs an additional 2 bytes, plus either one or 5 - bytes for a repeat. We also need to keep the value of the highest - back reference. */ +/* Give an error if there's back reference to a non-existent capturing +subpattern. */ - if (c <= -ESC_REF) - { - int refnum = -c - ESC_REF; - cd->backref_map |= (refnum < 32)? (1 << refnum) : 1; - if (refnum > cd->top_backref) - cd->top_backref = refnum; - length += 2; /* For single back reference */ - if (ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '?') ptr++; - } - } - continue; +if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; - case '^': /* Single-byte metacharacters */ - case '.': - case '$': - length++; - lastitemlength = 1; - continue; +/* Failed to compile, or error while post-processing */ - case '*': /* These repeats won't be after brackets; */ - case '+': /* those are handled separately */ - case '?': - length++; - goto POSESSIVE; /* A few lines below */ - - /* This covers the cases of braced repeats after a single char, metachar, - class, or back reference. */ - - case '{': - if (!is_counted_repeat(ptr+1)) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* These special cases just insert one extra opcode */ - - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; +if (errorcode != 0) + { + (pcre_free)(re); + PCRE_EARLY_ERROR_RETURN: + *erroroffset = ptr - (const uschar *)pattern; + PCRE_EARLY_ERROR_RETURN2: + *errorptr = find_error_text(errorcode); + if (errorcodeptr != NULL) *errorcodeptr = errorcode; + return NULL; + } - /* These cases might insert additional copies of a preceding character. */ +/* If the anchored option was not passed, set the flag if we can determine that +the pattern is anchored by virtue of ^ characters or \A or anything else (such +as starting with .* when DOTALL is set). - else - { - if (min != 1) - { - length -= lastitemlength; /* Uncount the original char or metachar */ - if (min > 0) length += 3 + lastitemlength; - } - length += lastitemlength + ((max > 0)? 3 : 1); - } - - if (ptr[1] == '?') ptr++; /* Needs no extra length */ - - POSESSIVE: /* Test for possessive quantifier */ - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; /* Allow for atomic brackets */ - } - continue; - - /* An alternation contains an offset to the next branch or ket. If any ims - options changed in the previous branch(es), and/or if we are in a - lookbehind assertion, extra space will be needed at the start of the - branch. This is handled by branch_extra. */ - - case '|': - length += 1 + LINK_SIZE + branch_extra; - continue; - - /* A character class uses 33 characters provided that all the character - values are less than 256. Otherwise, it uses a bit map for low valued - characters, and individual items for others. Don't worry about character - types that aren't allowed in classes - they'll get picked up during the - compile. A character class that contains only one single-byte character - uses 2 or 3 bytes, depending on whether it is negated or not. Notice this - where we can. (In UTF-8 mode we can do this only for chars < 128.) */ - - case '[': - if (*(++ptr) == '^') - { - class_optcount = 10; /* Greater than one */ - ptr++; - } - else class_optcount = 0; - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; -#endif - - /* Written as a "do" so that an initial ']' is taken as data */ - - if (*ptr != 0) do - { - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (*ptr != '\\' || ptr[1] != 'E') goto GET_ONE_CHARACTER; - inescq = FALSE; - ptr += 1; - continue; - } - - /* Outside \Q...\E, check for escapes */ - - if (*ptr == '\\') - { - c = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* \b is backspace inside a class; \X is literal */ - - if (-c == ESC_b) c = '\b'; - else if (-c == ESC_X) c = 'X'; - - /* \Q enters quoting mode */ - - else if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } - - /* Handle escapes that turn into characters */ - - if (c >= 0) goto NON_SPECIAL_CHARACTER; - - /* Escapes that are meta-things. The normal ones just affect the - bit map, but Unicode properties require an XCLASS extended item. */ - - else - { - class_optcount = 10; /* \d, \s etc; make sure > 1 */ -#ifdef SUPPORT_UTF8 - if (-c == ESC_p || -c == ESC_P) - { - if (!class_utf8) - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - length += 3; - } -#endif - } - } - - /* Check the syntax for POSIX stuff. The bits we actually handle are - checked during the real compile phase. */ - - else if (*ptr == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &ptr, cd)) - { - ptr++; - class_optcount = 10; /* Make sure > 1 */ - } - - /* Anything else increments the possible optimization count. We have to - detect ranges here so that we can compute the number of extra ranges for - caseless wide characters when UCP support is available. If there are wide - characters, we are going to have to use an XCLASS, even for single - characters. */ - - else - { - int d; - - GET_ONE_CHARACTER: - -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(c, ptr, extra); - ptr += extra; - } - else c = *ptr; -#else - c = *ptr; -#endif - - /* Come here from handling \ above when it escapes to a char value */ - - NON_SPECIAL_CHARACTER: - class_optcount++; - - d = -1; - if (ptr[1] == '-') - { - uschar const *hyptr = ptr++; - if (ptr[1] == '\\') - { - ptr++; - d = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if (-d == ESC_b) d = '\b'; /* backspace */ - else if (-d == ESC_X) d = 'X'; /* literal X in a class */ - } - else if (ptr[1] != 0 && ptr[1] != ']') - { - ptr++; -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(d, ptr, extra); - ptr += extra; - } - else -#endif - d = *ptr; - } - if (d < 0) ptr = hyptr; /* go back to hyphen as data */ - } - - /* If d >= 0 we have a range. In UTF-8 mode, if the end is > 255, or > - 127 for caseless matching, we will need to use an XCLASS. */ - - if (d >= 0) - { - class_optcount = 10; /* Ensure > 1 */ - if (d < c) - { - errorcode = ERR8; - goto PCRE_ERROR_RETURN; - } - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - uschar buffer[6]; - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - -#ifdef SUPPORT_UCP - /* If we have UCP support, find out how many extra ranges are - needed to map the other case of characters within this range. We - have to mimic the range optimization here, because extending the - range upwards might push d over a boundary that makes is use - another byte in the UTF-8 representation. */ - - if ((options & PCRE_CASELESS) != 0) - { - int occ, ocd; - int cc = c; - int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= c && ocd <= d) continue; /* Skip embedded */ - - if (occ < c && ocd >= c - 1) /* Extend the basic range */ - { /* if there is overlap, */ - c = occ; /* noting that if occ < c */ - continue; /* we can't have ocd > d */ - } /* because a subrange is */ - if (ocd > d && occ <= d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - /* An extra item is needed */ - - length += 1 + _pcre_ord2utf8(occ, buffer) + - ((occ == ocd)? 0 : _pcre_ord2utf8(ocd, buffer)); - } - } -#endif /* SUPPORT_UCP */ - - /* The length of the (possibly extended) range */ - - length += 1 + _pcre_ord2utf8(c, buffer) + _pcre_ord2utf8(d, buffer); - } -#endif /* SUPPORT_UTF8 */ - - } - - /* We have a single character. There is nothing to be done unless we - are in UTF-8 mode. If the char is > 255, or 127 when caseless, we must - allow for an XCL_SINGLE item, doubled for caselessness if there is UCP - support. */ - - else - { -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - uschar buffer[6]; - class_optcount = 10; /* Ensure > 1 */ - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } -#ifdef SUPPORT_UCP - length += (((options & PCRE_CASELESS) != 0)? 2 : 1) * - (1 + _pcre_ord2utf8(c, buffer)); -#else /* SUPPORT_UCP */ - length += 1 + _pcre_ord2utf8(c, buffer); -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - } - } - } - while (*(++ptr) != 0 && (inescq || *ptr != ']')); /* Concludes "do" above */ - - if (*ptr == 0) /* Missing terminating ']' */ - { - errorcode = ERR6; - goto PCRE_ERROR_RETURN; - } - - /* We can optimize when there was only one optimizable character. Repeats - for positive and negated single one-byte chars are handled by the general - code. Here, we handle repeats for the class opcodes. */ - - if (class_optcount == 1) length += 3; else - { - length += 33; - - /* A repeat needs either 1 or 5 bytes. If it is a possessive quantifier, - we also need extra for wrapping the whole thing in a sub-pattern. */ - - if (*ptr != 0 && ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - else if (ptr[1] == '?') ptr++; - } - } - continue; - - /* Brackets may be genuine groups or special things */ - - case '(': - branch_newextra = 0; - bracket_length = 1 + LINK_SIZE; - capturing = FALSE; - - /* Handle special forms of bracket, which all start (? */ - - if (ptr[1] == '?') - { - int set, unset; - int *optset; - - switch (c = ptr[2]) - { - /* Skip over comments entirely */ - case '#': - ptr += 3; - while (*ptr != 0 && *ptr != ')') ptr++; - if (*ptr == 0) - { - errorcode = ERR18; - goto PCRE_ERROR_RETURN; - } - continue; - - /* Non-referencing groups and lookaheads just move the pointer on, and - then behave like a non-special bracket, except that they don't increment - the count of extracting brackets. Ditto for the "once only" bracket, - which is in Perl from version 5.005. */ - - case ':': - case '=': - case '!': - case '>': - ptr += 2; - break; - - /* Named subpatterns are an extension copied from Python */ - - case 'P': - ptr += 3; - - /* Handle the definition of a named subpattern */ - - if (*ptr == '<') - { - const uschar *p; /* Don't amalgamate; some compilers */ - p = ++ptr; /* grumble at autoincrement in declaration */ - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != '>') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - name_count++; - if (name_count > MAX_NAME_COUNT) - { - errorcode = ERR49; - goto PCRE_ERROR_RETURN; - } - if (ptr - p > max_name_size) - { - max_name_size = (ptr - p); - if (max_name_size > MAX_NAME_SIZE) - { - errorcode = ERR48; - goto PCRE_ERROR_RETURN; - } - } - capturing = TRUE; /* Named parentheses are always capturing */ - break; /* Go handle capturing parentheses */ - } - - /* Handle back references and recursive calls to named subpatterns */ - - if (*ptr == '=' || *ptr == '>') - { - length += 3 + 3*LINK_SIZE; /* Allow for the automatic "once" */ - while ((cd->ctypes[*(++ptr)] & ctype_word) != 0); - if (*ptr != ')') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - goto RECURSE_CHECK_QUANTIFIED; - } - - /* Unknown character after (?P */ - - errorcode = ERR41; - goto PCRE_ERROR_RETURN; - - /* (?R) specifies a recursive call to the regex, which is an extension - to provide the facility which can be obtained by (?p{perl-code}) in - Perl 5.6. In Perl 5.8 this has become (??{perl-code}). - - From PCRE 4.00, items such as (?3) specify subroutine-like "calls" to - the appropriate numbered brackets. This includes both recursive and - non-recursive calls. (?R) is now synonymous with (?0). */ - - case 'R': - ptr++; - - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': - ptr += 2; - if (c != 'R') - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR29; - goto PCRE_ERROR_RETURN; - } - length += 3 + 3*LINK_SIZE; /* Allows for the automatic "once" */ - - /* If this item is quantified, it will get wrapped inside brackets so - as to use the code for quantified brackets. We jump down and use the - code that handles this for real brackets. Come here from code for - named recursions/subroutines. */ - - RECURSE_CHECK_QUANTIFIED: - if (ptr[1] == '+' || ptr[1] == '*' || ptr[1] == '?' || ptr[1] == '{') - { - length += 2 + 2 * LINK_SIZE; /* to make bracketed */ - duplength = 5 + 3 * LINK_SIZE; - goto HANDLE_QUANTIFIED_BRACKETS; - } - continue; - - /* (?C) is an extension which provides "callout" - to provide a bit of - the functionality of the Perl (?{...}) feature. An optional number may - follow (default is zero). */ - - case 'C': - ptr += 2; - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR39; - goto PCRE_ERROR_RETURN; - } - length += 2 + 2*LINK_SIZE; - continue; - - /* Lookbehinds are in Perl from version 5.005 */ - - case '<': - ptr += 3; - if (*ptr == '=' || *ptr == '!') - { - branch_newextra = 1 + LINK_SIZE; - length += 1 + LINK_SIZE; /* For the first branch */ - break; - } - errorcode = ERR24; - goto PCRE_ERROR_RETURN; - - /* Conditionals are in Perl from version 5.005. The bracket must either - be followed by a number (for bracket reference) or by an assertion - group. PCRE extends this by allowing a name to reference a named group; - unfortunately, previously 'R' was implemented for a recursion test. - When this is compiled, we look for the named group 'R' first. At this - point we just do a basic syntax check. */ - - case '(': - if ((cd->ctypes[ptr[3]] & ctype_word) != 0) - { - ptr += 4; - length += 3; - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != ')') - { - errorcode = ERR26; - goto PCRE_ERROR_RETURN; - } - } - else /* An assertion must follow */ - { - ptr++; /* Can treat like ':' as far as spacing is concerned */ - if (ptr[2] != '?' || - (ptr[3] != '=' && ptr[3] != '!' && ptr[3] != '<') ) - { - ptr += 2; /* To get right offset in message */ - errorcode = ERR28; - goto PCRE_ERROR_RETURN; - } - } - break; - - /* Else loop checking valid options until ) is met. Anything else is an - error. If we are without any brackets, i.e. at top level, the settings - act as if specified in the options, so massage the options immediately. - This is for backward compatibility with Perl 5.004. */ - - default: - set = unset = 0; - optset = &set; - ptr += 2; - - for (;; ptr++) - { - c = *ptr; - switch (c) - { - case 'i': - *optset |= PCRE_CASELESS; - continue; - - case 'J': - *optset |= PCRE_DUPNAMES; - options |= PCRE_JCHANGED; /* Record that it changed */ - continue; - - case 'm': - *optset |= PCRE_MULTILINE; - continue; - - case 's': - *optset |= PCRE_DOTALL; - continue; - - case 'x': - *optset |= PCRE_EXTENDED; - continue; - - case 'X': - *optset |= PCRE_EXTRA; - continue; - - case 'U': - *optset |= PCRE_UNGREEDY; - continue; - - case '-': - optset = &unset; - continue; - - /* A termination by ')' indicates an options-setting-only item; if - this is at the very start of the pattern (indicated by item_count - being zero), we use it to set the global options. This is helpful - when analyzing the pattern for first characters, etc. Otherwise - nothing is done here and it is handled during the compiling - process. - - We allow for more than one options setting at the start. If such - settings do not change the existing options, nothing is compiled. - However, we must leave space just in case something is compiled. - This can happen for pathological sequences such as (?i)(?-i) - because the global options will end up with -i set. The space is - small and not significant. (Before I did this there was a reported - bug with (?i)(?-i) in a machine-generated pattern.) - - [Historical note: Up to Perl 5.8, options settings at top level - were always global settings, wherever they appeared in the pattern. - That is, they were equivalent to an external setting. From 5.8 - onwards, they apply only to what follows (which is what you might - expect).] */ - - case ')': - if (item_count == 0) - { - options = (options | set) & (~unset); - set = unset = 0; /* To save length */ - item_count--; /* To allow for several */ - length += 2; - } - - /* Fall through */ - - /* A termination by ':' indicates the start of a nested group with - the given options set. This is again handled at compile time, but - we must allow for compiled space if any of the ims options are - set. We also have to allow for resetting space at the end of - the group, which is why 4 is added to the length and not just 2. - If there are several changes of options within the same group, this - will lead to an over-estimate on the length, but this shouldn't - matter very much. We also have to allow for resetting options at - the start of any alternations, which we do by setting - branch_newextra to 2. */ - - case ':': - if (((set|unset) & PCRE_IMS) != 0) - { - length += 4; - branch_newextra = 2; - } - goto END_OPTIONS; - - /* Unrecognized option character */ - - default: - errorcode = ERR12; - goto PCRE_ERROR_RETURN; - } - } - - /* If we hit a closing bracket, that's it - this is a freestanding - option-setting. We need to ensure that branch_extra is updated if - necessary. The only values branch_newextra can have here are 0 or 2. - If the value is 2, then branch_extra must either be 2 or 5, depending - on whether this is a lookbehind group or not. */ - - END_OPTIONS: - if (c == ')') - { - if (branch_newextra == 2 && - (branch_extra == 0 || branch_extra == 1+LINK_SIZE)) - branch_extra += branch_newextra; - continue; - } - - /* If options were terminated by ':' control comes here. This is a - non-capturing group with an options change. There is nothing more that - needs to be done because "capturing" is already set FALSE by default; - we can just fall through. */ - - } - } - - /* Ordinary parentheses, not followed by '?', are capturing unless - PCRE_NO_AUTO_CAPTURE is set. */ - - else capturing = (options & PCRE_NO_AUTO_CAPTURE) == 0; - - /* Capturing brackets must be counted so we can process escapes in a - Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to need - an additional 3 bytes of memory per capturing bracket. */ - - if (capturing) - { - bracount++; - if (bracount > EXTRACT_BASIC_MAX) bracket_length += 3; - } - - /* Save length for computing whole length at end if there's a repeat that - requires duplication of the group. Also save the current value of - branch_extra, and start the new group with the new value. If non-zero, this - will either be 2 for a (?imsx: group, or 3 for a lookbehind assertion. */ - - if (brastackptr >= sizeof(brastack)/sizeof(int)) - { - errorcode = ERR19; - goto PCRE_ERROR_RETURN; - } - - bralenstack[brastackptr] = branch_extra; - branch_extra = branch_newextra; - - brastack[brastackptr++] = length; - length += bracket_length; - continue; - - /* Handle ket. Look for subsequent max/min; for certain sets of values we - have to replicate this bracket up to that many times. If brastackptr is - 0 this is an unmatched bracket which will generate an error, but take care - not to try to access brastack[-1] when computing the length and restoring - the branch_extra value. */ - - case ')': - length += 1 + LINK_SIZE; - if (brastackptr > 0) - { - duplength = length - brastack[--brastackptr]; - branch_extra = bralenstack[brastackptr]; - /* This is a paranoid check to stop integer overflow later on */ - if (duplength > MAX_DUPLENGTH) - { - errorcode = ERR50; - goto PCRE_ERROR_RETURN; - } - } - else duplength = 0; - - /* The following code is also used when a recursion such as (?3) is - followed by a quantifier, because in that case, it has to be wrapped inside - brackets so that the quantifier works. The value of duplength must be - set before arrival. */ - - HANDLE_QUANTIFIED_BRACKETS: - - /* Leave ptr at the final char; for read_repeat_counts this happens - automatically; for the others we need an increment. */ - - if ((c = ptr[1]) == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - } - else if (c == '*') { min = 0; max = -1; ptr++; } - else if (c == '+') { min = 1; max = -1; ptr++; } - else if (c == '?') { min = 0; max = 1; ptr++; } - else { min = 1; max = 1; } - - /* If the minimum is zero, we have to allow for an OP_BRAZERO before the - group, and if the maximum is greater than zero, we have to replicate - maxval-1 times; each replication acquires an OP_BRAZERO plus a nesting - bracket set. */ - - if (min == 0) - { - length++; - if (max > 0) length += (max - 1) * (duplength + 3 + 2*LINK_SIZE); - } - - /* When the minimum is greater than zero, we have to replicate up to - minval-1 times, with no additions required in the copies. Then, if there - is a limited maximum we have to replicate up to maxval-1 times allowing - for a BRAZERO item before each optional copy and nesting brackets for all - but one of the optional copies. */ - - else - { - length += (min - 1) * duplength; - if (max > min) /* Need this test as max=-1 means no limit */ - length += (max - min) * (duplength + 3 + 2*LINK_SIZE) - - (2 + 2*LINK_SIZE); - } - - /* Allow space for once brackets for "possessive quantifier" */ - - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - continue; - - /* Non-special character. It won't be space or # in extended mode, so it is - always a genuine character. If we are in a \Q...\E sequence, check for the - end; if not, we have a literal. */ - - default: - NORMAL_CHAR: - - if (inescq && c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - - length += 2; /* For a one-byte character */ - lastitemlength = 1; /* Default length of last item for repeats */ - - /* In UTF-8 mode, check for additional bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) /* Can't flow over the end */ - { /* because the end is marked */ - lastitemlength++; /* by a zero byte. */ - length++; - ptr++; - } - } -#endif - - continue; - } - } - -length += 2 + LINK_SIZE; /* For final KET and END */ - -if ((options & PCRE_AUTO_CALLOUT) != 0) - length += 2 + 2*LINK_SIZE; /* For final callout */ - -if (length > MAX_PATTERN_SIZE) - { - errorcode = ERR20; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Compute the size of data block needed and get it, either from malloc or -externally provided function. Integer overflow should no longer be possible -because nowadays we limit the maximum value of name_count and max_name size. */ - -size = length + sizeof(real_pcre) + name_count * (max_name_size + 3); -re = (real_pcre *)(pcre_malloc)(size); - -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, options, and character table -pointer. NULL is used for the default character tables. The nullpad field is at -the end; it's there to help in the case when a regex compiled on a system with -4-byte pointers is run on another with 8-byte pointers. */ - -re->magic_number = MAGIC_NUMBER; -re->size = size; -re->options = options; -re->dummy1 = 0; -re->name_table_offset = sizeof(real_pcre); -re->name_entry_size = max_name_size + 3; -re->name_count = name_count; -re->ref_count = 0; -re->tables = (tables == _pcre_default_tables)? NULL : tables; -re->nullpad = NULL; - -/* The starting points of the name/number translation table and of the code are -passed around in the compile data block. */ - -cd->names_found = 0; -cd->name_entry_size = max_name_size + 3; -cd->name_table = (uschar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->start_pattern = (const uschar *)pattern; -cd->req_varyopt = 0; -cd->nopartial = FALSE; - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, errorcode will be set non-zero, so we don't need to look at the result -of the function here. */ - -ptr = (const uschar *)pattern; -code = (uschar *)codestart; -*code = OP_BRA; -bracount = 0; -(void)compile_regex(options, options & PCRE_IMS, &bracount, &code, &ptr, - &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd); -re->top_bracket = bracount; -re->top_backref = cd->top_backref; - -if (cd->nopartial) re->options |= PCRE_NOPARTIAL; - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (errorcode == 0 && *ptr != 0) errorcode = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef PCRE_DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (pcre_free)(re); - PCRE_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; - PCRE_EARLY_ERROR_RETURN: - *errorptr = error_texts[errorcode]; - if (errorcodeptr != NULL) *errorcodeptr = errorcode; - return NULL; - } - -/* If the anchored option was not passed, set the flag if we can determine that -the pattern is anchored by virtue of ^ characters or \A or anything else (such -as starting with .* when DOTALL is set). - -Otherwise, if we know what the first character has to be, save it, because that +Otherwise, if we know what the first byte has to be, save it, because that speeds up unanchored matches no end. If not, see if we can set the PCRE_STARTLINE flag. This is helpful for multiline matches when all branches start with ^. and also when all branches start with .* for non-DOTALL matches. */ -if ((options & PCRE_ANCHORED) == 0) +if ((re->options & PCRE_ANCHORED) == 0) { - int temp_options = options; + int temp_options = re->options; /* May get changed during these scans */ if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) re->options |= PCRE_ANCHORED; else @@ -5200,10 +6536,10 @@ int ch = firstbyte & 255; re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && cd->fcc[ch] == ch)? ch : firstbyte; - re->options |= PCRE_FIRSTSET; + re->flags |= PCRE_FIRSTSET; } else if (is_startline(codestart, 0, cd->backref_map)) - re->options |= PCRE_STARTLINE; + re->flags |= PCRE_STARTLINE; } } @@ -5217,7 +6553,7 @@ int ch = reqbyte & 255; re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; - re->options |= PCRE_REQCHSET; + re->flags |= PCRE_REQCHSET; } /* Print out the compiled data if debugging is enabled. This is never the @@ -5228,21 +6564,9 @@ printf("Length = %d top_bracket = %d top_backref = %d\n", length, re->top_bracket, re->top_backref); -if (re->options != 0) - { - printf("%s%s%s%s%s%s%s%s%s\n", - ((re->options & PCRE_NOPARTIAL) != 0)? "nopartial " : "", - ((re->options & PCRE_ANCHORED) != 0)? "anchored " : "", - ((re->options & PCRE_CASELESS) != 0)? "caseless " : "", - ((re->options & PCRE_EXTENDED) != 0)? "extended " : "", - ((re->options & PCRE_MULTILINE) != 0)? "multiline " : "", - ((re->options & PCRE_DOTALL) != 0)? "dotall " : "", - ((re->options & PCRE_DOLLAR_ENDONLY) != 0)? "endonly " : "", - ((re->options & PCRE_EXTRA) != 0)? "extra " : "", - ((re->options & PCRE_UNGREEDY) != 0)? "ungreedy " : ""); - } +printf("Options=%08x\n", re->options); -if ((re->options & PCRE_FIRSTSET) != 0) +if ((re->flags & PCRE_FIRSTSET) != 0) { int ch = re->first_byte & 255; const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? @@ -5251,7 +6575,7 @@ else printf("First char = \\x%02x%s\n", ch, caseless); } -if ((re->options & PCRE_REQCHSET) != 0) +if ((re->flags & PCRE_REQCHSET) != 0) { int ch = re->req_byte & 255; const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? @@ -5260,7 +6584,7 @@ else printf("Req char = \\x%02x%s\n", ch, caseless); } -pcre_printint(re, stdout); +pcre_printint(re, stdout, TRUE); /* This check is done here in the debugging case so that the code that was compiled can be seen. */ @@ -5268,12 +6592,12 @@ if (code - codestart > length) { (pcre_free)(re); - *errorptr = error_texts[ERR23]; + *errorptr = find_error_text(ERR23); *erroroffset = ptr - (uschar *)pattern; if (errorcodeptr != NULL) *errorcodeptr = ERR23; return NULL; } -#endif +#endif /* PCRE_DEBUG */ return (pcre *)re; } Modified: freeswitch/trunk/libs/pcre/pcre_config.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_config.c (original) +++ freeswitch/trunk/libs/pcre/pcre_config.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -41,6 +41,10 @@ /* This module contains the external function pcre_config(). */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -58,7 +62,7 @@ Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_config(int what, void *where) { switch (what) @@ -83,6 +87,14 @@ *((int *)where) = NEWLINE; break; + case PCRE_CONFIG_BSR: +#ifdef BSR_ANYCRLF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + case PCRE_CONFIG_LINK_SIZE: *((int *)where) = LINK_SIZE; break; @@ -92,11 +104,11 @@ break; case PCRE_CONFIG_MATCH_LIMIT: - *((unsigned int *)where) = MATCH_LIMIT; + *((unsigned long int *)where) = MATCH_LIMIT; break; case PCRE_CONFIG_MATCH_LIMIT_RECURSION: - *((unsigned int *)where) = MATCH_LIMIT_RECURSION; + *((unsigned long int *)where) = MATCH_LIMIT_RECURSION; break; case PCRE_CONFIG_STACKRECURSE: Modified: freeswitch/trunk/libs/pcre/pcre_dfa_exec.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_dfa_exec.c (original) +++ freeswitch/trunk/libs/pcre/pcre_dfa_exec.c Mon Jun 8 18:51:30 2009 @@ -3,10 +3,11 @@ *************************************************/ /* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. +and semantics are as close as possible to those of the Perl 5 language (but see +below for why this module is different). Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -39,11 +40,19 @@ /* This module contains the external function pcre_dfa_exec(), which is an -alternative matching function that uses a DFA algorithm. This is NOT Perl- -compatible, but it has advantages in certain applications. */ +alternative matching function that uses a sort of DFA algorithm (not a true +FSM). This is NOT Perl- compatible, but it has advantages in certain +applications. */ -#define NLBLOCK md /* The block containing newline information */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + #include "pcre_internal.h" @@ -52,30 +61,36 @@ #define SP " " - /************************************************* * Code parameters and static tables * *************************************************/ /* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes -into others, under special conditions. A gap of 10 between the blocks should be -enough. */ - -#define OP_PROP_EXTRA (EXTRACT_BASIC_MAX+1) -#define OP_EXTUNI_EXTRA (EXTRACT_BASIC_MAX+11) +into others, under special conditions. A gap of 20 between the blocks should be +enough. The resulting opcodes don't have to be less than 256 because they are +never stored, so we push them well clear of the normal opcodes. */ + +#define OP_PROP_EXTRA 300 +#define OP_EXTUNI_EXTRA 320 +#define OP_ANYNL_EXTRA 340 +#define OP_HSPACE_EXTRA 360 +#define OP_VSPACE_EXTRA 380 /* This table identifies those opcodes that are followed immediately by a character that is to be tested in some way. This makes is possible to centralize the loading of these characters. In the case of Type * etc, the "character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a -small value. */ +small value. ***NOTE*** If the start of this table is modified, the two tables +that follow must also be modified. */ -static uschar coptable[] = { +static const uschar coptable[] = { 0, /* End */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* \A, \G, \B, \b, \D, \d, \S, \s, \W, \w */ - 0, 0, /* Any, Anybyte */ + 0, 0, 0, 0, 0, /* \A, \G, \K, \B, \b */ + 0, 0, 0, 0, 0, 0, /* \D, \d, \S, \s, \W, \w */ + 0, 0, 0, /* Any, AllAny, Anybyte */ 0, 0, 0, /* NOTPROP, PROP, EXTUNI */ + 0, 0, 0, 0, 0, /* \R, \H, \h, \V, \v */ 0, 0, 0, 0, 0, /* \Z, \z, Opt, ^, $ */ 1, /* Char */ 1, /* Charnc */ @@ -83,12 +98,15 @@ /* Positive single-char repeats */ 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ 3, 3, 3, /* upto, minupto, exact */ + 1, 1, 1, 3, /* *+, ++, ?+, upto+ */ /* Negative single-char repeats - only for chars < 256 */ 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ 3, 3, 3, /* NOT upto, minupto, exact */ + 1, 1, 1, 3, /* NOT *+, ++, ?+, updo+ */ /* Positive type repeats */ 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ 3, 3, 3, /* Type upto, minupto, exact */ + 1, 1, 1, 3, /* Type *+, ++, ?+, upto+ */ /* Character class & ref repeats */ 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ 0, 0, /* CRRANGE, CRMINRANGE */ @@ -107,31 +125,33 @@ 0, /* Assert behind */ 0, /* Assert behind not */ 0, /* Reverse */ - 0, /* Once */ - 0, /* COND */ + 0, 0, 0, 0, /* ONCE, BRA, CBRA, COND */ + 0, 0, 0, /* SBRA, SCBRA, SCOND */ 0, /* CREF */ + 0, /* RREF */ + 0, /* DEF */ 0, 0, /* BRAZERO, BRAMINZERO */ - 0, /* BRANUMBER */ - 0 /* BRA */ + 0, 0, 0, 0, /* PRUNE, SKIP, THEN, COMMIT */ + 0, 0, 0 /* FAIL, ACCEPT, SKIPZERO */ }; /* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, and \w */ -static uschar toptable1[] = { - 0, 0, 0, 0, 0, +static const uschar toptable1[] = { + 0, 0, 0, 0, 0, 0, ctype_digit, ctype_digit, ctype_space, ctype_space, ctype_word, ctype_word, - 0 /* OP_ANY */ + 0, 0 /* OP_ANY, OP_ALLANY */ }; -static uschar toptable2[] = { - 0, 0, 0, 0, 0, +static const uschar toptable2[] = { + 0, 0, 0, 0, 0, 0, ctype_digit, 0, ctype_space, 0, ctype_word, 0, - 1 /* OP_ANY */ + 1, 1 /* OP_ANY, OP_ALLANY */ }; @@ -203,8 +223,8 @@ rlevel function call recursion level recursing regex recursive call level -Returns: > 0 => - = 0 => +Returns: > 0 => number of match offset pairs placed in offsets + = 0 => offsets overflowed; longest matches are present -1 => failed to match < -1 => some kind of unexpected problem @@ -278,7 +298,7 @@ const uschar *ctypes, *lcc, *fcc; const uschar *ptr; -const uschar *end_code; +const uschar *end_code, *first_op; int active_count, new_count, match_count; @@ -291,6 +311,8 @@ #ifdef SUPPORT_UTF8 BOOL utf8 = (md->poptions & PCRE_UTF8) != 0; +#else +BOOL utf8 = FALSE; #endif rlevel++; @@ -314,6 +336,9 @@ next_new_state = new_states = active_states + wscount; new_count = 0; +first_op = this_start_code + 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); + /* The first thing in any (sub) pattern is a bracket of some sort. Push all the alternative states onto the list, and find out where the end is. This makes is possible to use this function recursively, when we want to stop at a @@ -323,7 +348,7 @@ a backward assertion. In that case, we have to find out the maximum amount to move back, and set up each alternative appropriately. */ -if (this_start_code[1+LINK_SIZE] == OP_REVERSE) +if (*first_op == OP_REVERSE) { int max_back = 0; int gone_back; @@ -405,10 +430,13 @@ else { + int length = 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); do { - ADD_NEW(end_code - start_code + 1 + LINK_SIZE, 0); + ADD_NEW(end_code - start_code + length, 0); end_code += GET(end_code, 1); + length = 1 + LINK_SIZE; } while (*end_code == OP_ALT); } @@ -461,7 +489,7 @@ if (ptr < end_subject) { - clen = 1; + clen = 1; /* Number of bytes in the character */ #ifdef SUPPORT_UTF8 if (utf8) { GETCHARLEN(c, ptr, clen); } else #endif /* SUPPORT_UTF8 */ @@ -469,8 +497,8 @@ } else { - clen = 0; /* At end subject */ - c = -1; + clen = 0; /* This indicates the end of the subject */ + c = NOTACHAR; /* This value should never actually be used */ } /* Scan up the active states and act on each one. The result of an action @@ -483,12 +511,11 @@ stateblock *current_state = active_states + i; const uschar *code; int state_offset = current_state->offset; - int count, codevalue; - int chartype, script; + int count, codevalue, rrc; #ifdef PCRE_DEBUG printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); - if (c < 0) printf("-1\n"); + if (clen == 0) printf("EOL\n"); else if (c > 32 && c < 127) printf("'%c'\n", c); else printf("0x%02x\n", c); #endif @@ -532,7 +559,6 @@ code = start_code + state_offset; codevalue = *code; - if (codevalue >= OP_BRA) codevalue = OP_BRA; /* All brackets are equal */ /* If this opcode is followed by an inline character, load it. It is tempting to test for the presence of a subject character here, but that @@ -540,10 +566,10 @@ permitted. We also use this mechanism for opcodes such as OP_TYPEPLUS that take an - argument that is not a data character - but is always one byte long. - Unfortunately, we have to take special action to deal with \P, \p, and - \X in this case. To keep the other cases fast, convert these ones to new - opcodes. */ + argument that is not a data character - but is always one byte long. We + have to take special action to deal with \P, \p, \H, \h, \V, \v and \X in + this case. To keep the other cases fast, convert these ones to new opcodes. + */ if (coptable[codevalue] > 0) { @@ -554,15 +580,25 @@ d = code[coptable[codevalue]]; if (codevalue >= OP_TYPESTAR) { - if (d == OP_ANYBYTE) return PCRE_ERROR_DFA_UITEM; - if (d >= OP_NOTPROP) - codevalue += (d == OP_EXTUNI)? OP_EXTUNI_EXTRA : OP_PROP_EXTRA; + switch(d) + { + case OP_ANYBYTE: return PCRE_ERROR_DFA_UITEM; + case OP_NOTPROP: + case OP_PROP: codevalue += OP_PROP_EXTRA; break; + case OP_ANYNL: codevalue += OP_ANYNL_EXTRA; break; + case OP_EXTUNI: codevalue += OP_EXTUNI_EXTRA; break; + case OP_NOT_HSPACE: + case OP_HSPACE: codevalue += OP_HSPACE_EXTRA; break; + case OP_NOT_VSPACE: + case OP_VSPACE: codevalue += OP_VSPACE_EXTRA; break; + default: break; + } } } else { dlen = 0; /* Not strictly necessary, but compilers moan */ - d = -1; /* if these variables are not set. */ + d = NOTACHAR; /* if these variables are not set. */ } @@ -624,6 +660,7 @@ /*-----------------------------------------------------------------*/ case OP_BRA: + case OP_SBRA: do { ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); @@ -633,6 +670,18 @@ break; /*-----------------------------------------------------------------*/ + case OP_CBRA: + case OP_SCBRA: + ADD_ACTIVE(code - start_code + 3 + LINK_SIZE, 0); + code += GET(code, 1); + while (*code == OP_ALT) + { + ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); + code += GET(code, 1); + } + break; + + /*-----------------------------------------------------------------*/ case OP_BRAZERO: case OP_BRAMINZERO: ADD_ACTIVE(state_offset + 1, 0); @@ -642,17 +691,18 @@ break; /*-----------------------------------------------------------------*/ - case OP_BRANUMBER: - ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); + case OP_SKIPZERO: + code += 1 + GET(code, 2); + while (*code == OP_ALT) code += GET(code, 1); + ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); break; /*-----------------------------------------------------------------*/ case OP_CIRC: if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || ((ims & PCRE_MULTILINE) != 0 && - ptr >= start_subject + md->nllen && ptr != end_subject && - IS_NEWLINE(ptr - md->nllen))) + WAS_NEWLINE(ptr))) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -686,16 +736,19 @@ /*-----------------------------------------------------------------*/ case OP_ANY: - if (clen > 0 && ((ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr))) + if (clen > 0 && !IS_NEWLINE(ptr)) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_ALLANY: + if (clen > 0) { ADD_NEW(state_offset + 1, 0); } break; /*-----------------------------------------------------------------*/ case OP_EODN: - if (clen == 0 || - (ptr == end_subject - md->nllen && IS_NEWLINE(ptr))) + if (clen == 0 || (IS_NEWLINE(ptr) && ptr == end_subject - md->nllen)) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -704,13 +757,12 @@ if ((md->moptions & PCRE_NOTEOL) == 0) { if (clen == 0 || - (ptr <= end_subject - md->nllen && IS_NEWLINE(ptr) && + ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr) && ((ims & PCRE_MULTILINE) != 0 || ptr == end_subject - md->nllen) )) { ADD_ACTIVE(state_offset + 1, 0); } } - else if ((ims & PCRE_MULTILINE) != 0 && - ptr <= end_subject - md->nllen && IS_NEWLINE(ptr)) + else if ((ims & PCRE_MULTILINE) != 0 && IS_NEWLINE(ptr)) { ADD_ACTIVE(state_offset + 1, 0); } break; @@ -759,19 +811,18 @@ break; -#ifdef SUPPORT_UCP - /*-----------------------------------------------------------------*/ /* Check the next character by Unicode property. We will get here only if the support is in the binary; otherwise a compile-time error occurs. */ +#ifdef SUPPORT_UCP case OP_PROP: case OP_NOTPROP: if (clen > 0) { BOOL OK; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record * prop = GET_UCD(c); switch(code[1]) { case PT_ANY: @@ -779,19 +830,19 @@ break; case PT_LAMP: - OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; break; case PT_GC: - OK = category == code[2]; + OK = _pcre_ucp_gentype[prop->chartype] == code[2]; break; case PT_PC: - OK = chartype == code[2]; + OK = prop->chartype == code[2]; break; case PT_SC: - OK = script == code[2]; + OK = prop->script == code[2]; break; /* Should never occur, but keep compilers from grumbling. */ @@ -811,24 +862,26 @@ /* ========================================================================== */ /* These opcodes likewise inspect the subject character, but have an argument that is not a data character. It is one of these opcodes: - OP_ANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, OP_WORDCHAR, - OP_NOT_WORDCHAR. The value is loaded into d. */ + OP_ANY, OP_ALLANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, + OP_WORDCHAR, OP_NOT_WORDCHAR. The value is loaded into d. */ case OP_TYPEPLUS: case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } if (clen > 0) { if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || (c < 256 && - (d != OP_ANY || - (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr) - ) && + (d != OP_ANY || !IS_NEWLINE(ptr)) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (count > 0 && codevalue == OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } count++; ADD_NEW(state_offset, count); } @@ -838,18 +891,20 @@ /*-----------------------------------------------------------------*/ case OP_TYPEQUERY: case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: ADD_ACTIVE(state_offset + 2, 0); if (clen > 0) { if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || (c < 256 && - (d != OP_ANY || - (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr) - ) && + (d != OP_ANY || !IS_NEWLINE(ptr)) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (codevalue == OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } ADD_NEW(state_offset + 2, 0); } } @@ -858,18 +913,20 @@ /*-----------------------------------------------------------------*/ case OP_TYPESTAR: case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: ADD_ACTIVE(state_offset + 2, 0); if (clen > 0) { if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || (c < 256 && - (d != OP_ANY || - (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr) - ) && + (d != OP_ANY || !IS_NEWLINE(ptr)) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (codevalue == OP_TYPEPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } ADD_NEW(state_offset, 0); } } @@ -877,22 +934,40 @@ /*-----------------------------------------------------------------*/ case OP_TYPEEXACT: + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + 4, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ case OP_TYPEUPTO: case OP_TYPEMINUPTO: - if (codevalue != OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } + case OP_TYPEPOSUPTO: + ADD_ACTIVE(state_offset + 4, 0); count = current_state->count; /* Number already matched */ if (clen > 0) { if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || (c < 256 && - (d != OP_ANY || - (ims & PCRE_DOTALL) != 0 || - ptr > end_subject - md->nllen || - !IS_NEWLINE(ptr) - ) && + (d != OP_ANY || !IS_NEWLINE(ptr)) && ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) { + if (codevalue == OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } if (++count >= GET2(code, 1)) { ADD_NEW(state_offset + 4, 0); } else @@ -903,18 +978,20 @@ /* ========================================================================== */ /* These are virtual opcodes that are used when something like - OP_TYPEPLUS has OP_PROP, OP_NOTPROP, or OP_EXTUNI as its argument. It - keeps the code above fast for the other cases. The argument is in the - d variable. */ + OP_TYPEPLUS has OP_PROP, OP_NOTPROP, OP_ANYNL, or OP_EXTUNI as its + argument. It keeps the code above fast for the other cases. The argument + is in the d variable. */ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEPLUS: case OP_PROP_EXTRA + OP_TYPEMINPLUS: + case OP_PROP_EXTRA + OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } if (clen > 0) { BOOL OK; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record * prop = GET_UCD(c); switch(code[2]) { case PT_ANY: @@ -922,19 +999,19 @@ break; case PT_LAMP: - OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; break; case PT_GC: - OK = category == code[3]; + OK = _pcre_ucp_gentype[prop->chartype] == code[3]; break; case PT_PC: - OK = chartype == code[3]; + OK = prop->chartype == code[3]; break; case PT_SC: - OK = script == code[3]; + OK = prop->script == code[3]; break; /* Should never occur, but keep compilers from grumbling. */ @@ -944,25 +1021,40 @@ break; } - if (OK == (d == OP_PROP)) { count++; ADD_NEW(state_offset, count); } + if (OK == (d == OP_PROP)) + { + if (count > 0 && codevalue == OP_PROP_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } } break; /*-----------------------------------------------------------------*/ case OP_EXTUNI_EXTRA + OP_TYPEPLUS: case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: + case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + if (clen > 0 && UCD_CATEGORY(c) != ucp_M) { const uschar *nptr = ptr + clen; int ncount = 0; + if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; int ndlen = 1; GETCHARLEN(nd, nptr, ndlen); - if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + if (UCD_CATEGORY(nd) != ucp_M) break; ncount++; nptr += ndlen; } @@ -970,15 +1062,149 @@ ADD_NEW_DATA(-state_offset, count, ncount); } break; +#endif /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEPLUS: + case OP_ANYNL_EXTRA + OP_TYPEMINPLUS: + case OP_ANYNL_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL01; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL01: + case 0x000a: + if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, ncount); + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEPLUS: + case OP_VSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_VSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_VSPACE)) + { + if (count > 0 && codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEPLUS: + case OP_HSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_HSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (count > 0 && codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEQUERY: case OP_PROP_EXTRA + OP_TYPEMINQUERY: + case OP_PROP_EXTRA + OP_TYPEPOSQUERY: count = 4; goto QS1; case OP_PROP_EXTRA + OP_TYPESTAR: case OP_PROP_EXTRA + OP_TYPEMINSTAR: + case OP_PROP_EXTRA + OP_TYPEPOSSTAR: count = 0; QS1: @@ -987,7 +1213,7 @@ if (clen > 0) { BOOL OK; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record * prop = GET_UCD(c); switch(code[2]) { case PT_ANY: @@ -995,19 +1221,19 @@ break; case PT_LAMP: - OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; break; case PT_GC: - OK = category == code[3]; + OK = _pcre_ucp_gentype[prop->chartype] == code[3]; break; case PT_PC: - OK = chartype == code[3]; + OK = prop->chartype == code[3]; break; case PT_SC: - OK = script == code[3]; + OK = prop->script == code[3]; break; /* Should never occur, but keep compilers from grumbling. */ @@ -1017,51 +1243,224 @@ break; } - if (OK == (d == OP_PROP)) { ADD_NEW(state_offset + count, 0); } + if (OK == (d == OP_PROP)) + { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_PROP_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + count, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_EXTUNI_EXTRA + OP_TYPEQUERY: case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: + case OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY: count = 2; goto QS2; case OP_EXTUNI_EXTRA + OP_TYPESTAR: case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: + case OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR: count = 0; QS2: ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + if (clen > 0 && UCD_CATEGORY(c) != ucp_M) { const uschar *nptr = ptr + clen; int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; int ndlen = 1; GETCHARLEN(nd, nptr, ndlen); - if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + if (UCD_CATEGORY(nd) != ucp_M) break; ncount++; nptr += ndlen; } ADD_NEW_DATA(-(state_offset + count), 0, ncount); } break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEQUERY: + case OP_ANYNL_EXTRA + OP_TYPEMINQUERY: + case OP_ANYNL_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS3; + + case OP_ANYNL_EXTRA + OP_TYPESTAR: + case OP_ANYNL_EXTRA + OP_TYPEMINSTAR: + case OP_ANYNL_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS3: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL02; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL02: + case 0x000a: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, ncount); + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEQUERY: + case OP_VSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_VSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS4; + + case OP_VSPACE_EXTRA + OP_TYPESTAR: + case OP_VSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_VSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS4: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEQUERY: + case OP_HSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_HSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS5; + + case OP_HSPACE_EXTRA + OP_TYPESTAR: + case OP_HSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_HSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS5: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + count), 0, 0); + } + } + break; /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP case OP_PROP_EXTRA + OP_TYPEEXACT: case OP_PROP_EXTRA + OP_TYPEUPTO: case OP_PROP_EXTRA + OP_TYPEMINUPTO: + case OP_PROP_EXTRA + OP_TYPEPOSUPTO: if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) { ADD_ACTIVE(state_offset + 6, 0); } count = current_state->count; /* Number already matched */ if (clen > 0) { BOOL OK; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record * prop = GET_UCD(c); switch(code[4]) { case PT_ANY: @@ -1069,19 +1468,19 @@ break; case PT_LAMP: - OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; break; case PT_GC: - OK = category == code[5]; + OK = _pcre_ucp_gentype[prop->chartype] == code[5]; break; case PT_PC: - OK = chartype == code[5]; + OK = prop->chartype == code[5]; break; case PT_SC: - OK = script == code[5]; + OK = prop->script == code[5]; break; /* Should never occur, but keep compilers from grumbling. */ @@ -1093,6 +1492,11 @@ if (OK == (d == OP_PROP)) { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } if (++count >= GET2(code, 1)) { ADD_NEW(state_offset + 6, 0); } else @@ -1105,19 +1509,25 @@ case OP_EXTUNI_EXTRA + OP_TYPEEXACT: case OP_EXTUNI_EXTRA + OP_TYPEUPTO: case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: + case OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO: if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) { ADD_ACTIVE(state_offset + 4, 0); } count = current_state->count; /* Number already matched */ - if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + if (clen > 0 && UCD_CATEGORY(c) != ucp_M) { const uschar *nptr = ptr + clen; int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } while (nptr < end_subject) { int nd; int ndlen = 1; GETCHARLEN(nd, nptr, ndlen); - if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + if (UCD_CATEGORY(nd) != ucp_M) break; ncount++; nptr += ndlen; } @@ -1127,6 +1537,148 @@ { ADD_NEW_DATA(-state_offset, count, ncount); } } break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEEXACT: + case OP_ANYNL_EXTRA + OP_TYPEUPTO: + case OP_ANYNL_EXTRA + OP_TYPEMINUPTO: + case OP_ANYNL_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_ANYNL_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL03; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL03: + case 0x000a: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, ncount); } + else + { ADD_NEW_DATA(-state_offset, count, ncount); } + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEEXACT: + case OP_VSPACE_EXTRA + OP_TYPEUPTO: + case OP_VSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_VSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_VSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + OK = TRUE; + break; + + default: + OK = FALSE; + } + + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEEXACT: + case OP_HSPACE_EXTRA + OP_TYPEUPTO: + case OP_HSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_HSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_HSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; /* ========================================================================== */ /* These opcodes are followed by a character that is usually compared @@ -1148,16 +1700,16 @@ { if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else { - int othercase; + unsigned int othercase; if (c < 128) othercase = fcc[c]; else /* If we have Unicode property support, we can use it to test the other case of the character. */ #ifdef SUPPORT_UCP - othercase = _pcre_ucp_othercase(c); + othercase = UCD_OTHERCASE(c); #else - othercase = -1; + othercase = NOTACHAR; #endif if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } @@ -1180,7 +1732,7 @@ to wait for them to pass before continuing. */ case OP_EXTUNI: - if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + if (clen > 0 && UCD_CATEGORY(c) != ucp_M) { const uschar *nptr = ptr + clen; int ncount = 0; @@ -1188,7 +1740,7 @@ { int nclen = 1; GETCHARLEN(c, nptr, nclen); - if (_pcre_ucp_findprop(c, &chartype, &script) != ucp_M) break; + if (UCD_CATEGORY(c) != ucp_M) break; ncount++; nptr += nclen; } @@ -1198,6 +1750,134 @@ #endif /*-----------------------------------------------------------------*/ + /* This is a tricky like EXTUNI because it too can match more than one + character (when CR is followed by LF). In this case, set up a negative + state to wait for one character to pass before continuing. */ + + case OP_ANYNL: + if (clen > 0) switch(c) + { + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + + case 0x000a: + ADD_NEW(state_offset + 1, 0); + break; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) + { + ADD_NEW_DATA(-(state_offset + 1), 0, 1); + } + else + { + ADD_NEW(state_offset + 1, 0); + } + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_VSPACE: + if (clen > 0) switch(c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE: + if (clen > 0) switch(c) + { + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x0085: + case 0x2028: + case 0x2029: + ADD_NEW(state_offset + 1, 0); + break; + + default: break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_HSPACE: + if (clen > 0) switch(c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE: + if (clen > 0) switch(c) + { + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ /* Match a negated single character. This is only used for one-byte characters, that is, we know that d < 256. The character we are checking (c) can be multibyte. */ @@ -1205,7 +1885,7 @@ case OP_NOT: if (clen > 0) { - int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; + unsigned int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; if (c != d && c != otherd) { ADD_NEW(state_offset + dlen + 1, 0); } } break; @@ -1213,20 +1893,22 @@ /*-----------------------------------------------------------------*/ case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_NOTPLUS: case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: count = current_state->count; /* Already matched */ if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 if (utf8 && d >= 128) { #ifdef SUPPORT_UCP - otherd = _pcre_ucp_othercase(d); + otherd = UCD_OTHERCASE(d); #endif /* SUPPORT_UCP */ } else @@ -1234,26 +1916,37 @@ otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { count++; ADD_NEW(state_offset, count); } + { + if (count > 0 && + (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS)) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } } break; /*-----------------------------------------------------------------*/ case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: case OP_NOTQUERY: case OP_NOTMINQUERY: + case OP_NOTPOSQUERY: ADD_ACTIVE(state_offset + dlen + 1, 0); if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 if (utf8 && d >= 128) { #ifdef SUPPORT_UCP - otherd = _pcre_ucp_othercase(d); + otherd = UCD_OTHERCASE(d); #endif /* SUPPORT_UCP */ } else @@ -1261,26 +1954,35 @@ otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { ADD_NEW(state_offset + dlen + 1, 0); } + { + if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + dlen + 1, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_NOTSTAR: case OP_NOTMINSTAR: + case OP_NOTPOSSTAR: ADD_ACTIVE(state_offset + dlen + 1, 0); if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 if (utf8 && d >= 128) { #ifdef SUPPORT_UCP - otherd = _pcre_ucp_othercase(d); + otherd = UCD_OTHERCASE(d); #endif /* SUPPORT_UCP */ } else @@ -1288,30 +1990,66 @@ otherd = fcc[d]; } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { ADD_NEW(state_offset, 0); } + { + if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset, 0); + } } break; /*-----------------------------------------------------------------*/ case OP_EXACT: + case OP_NOTEXACT: + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + unsigned int otherd = NOTACHAR; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + dlen + 3, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ case OP_UPTO: case OP_MINUPTO: - case OP_NOTEXACT: + case OP_POSUPTO: case OP_NOTUPTO: case OP_NOTMINUPTO: - if (codevalue != OP_EXACT && codevalue != OP_NOTEXACT) - { ADD_ACTIVE(state_offset + dlen + 3, 0); } + case OP_NOTPOSUPTO: + ADD_ACTIVE(state_offset + dlen + 3, 0); count = current_state->count; /* Number already matched */ if (clen > 0) { - int otherd = -1; + unsigned int otherd = NOTACHAR; if ((ims & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UTF8 if (utf8 && d >= 128) { #ifdef SUPPORT_UCP - otherd = _pcre_ucp_othercase(d); + otherd = UCD_OTHERCASE(d); #endif /* SUPPORT_UCP */ } else @@ -1320,6 +2058,11 @@ } if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) { + if (codevalue == OP_POSUPTO || codevalue == OP_NOTPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } if (++count >= GET2(code, 1)) { ADD_NEW(state_offset + dlen + 3, 0); } else @@ -1414,7 +2157,12 @@ /* ========================================================================== */ /* These are the opcodes for fancy brackets of various kinds. We have - to use recursion in order to handle them. */ + to use recursion in order to handle them. The "always failing" assersion + (?!) is optimised when compiling to OP_FAIL, so we have to support that, + though the other "backtracking verbs" are not supported. */ + + case OP_FAIL: + break; case OP_ASSERT: case OP_ASSERT_NOT: @@ -1448,20 +2196,63 @@ /*-----------------------------------------------------------------*/ case OP_COND: + case OP_SCOND: { int local_offsets[1000]; int local_workspace[1000]; - int condcode = code[LINK_SIZE+1]; + int codelink = GET(code, 1); + int condcode; - /* The only supported version of OP_CREF is for the value 0xffff, which - means "test if in a recursion". */ + /* Because of the way auto-callout works during compile, a callout item + is inserted between OP_COND and an assertion condition. This does not + happen for the other conditions. */ - if (condcode == OP_CREF) + if (code[LINK_SIZE+1] == OP_CALLOUT) + { + rrc = 0; + if (pcre_callout != NULL) + { + pcre_callout_block cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = code[LINK_SIZE+2]; + cb.offset_vector = offsets; + cb.subject = (PCRE_SPTR)start_subject; + cb.subject_length = end_subject - start_subject; + cb.start_match = current_subject - start_subject; + cb.current_position = ptr - start_subject; + cb.pattern_position = GET(code, LINK_SIZE + 3); + cb.next_item_length = GET(code, 3 + 2*LINK_SIZE); + cb.capture_top = 1; + cb.capture_last = -1; + cb.callout_data = md->callout_data; + if ((rrc = (*pcre_callout)(&cb)) < 0) return rrc; /* Abandon */ + } + if (rrc > 0) break; /* Fail this thread */ + code += _pcre_OP_lengths[OP_CALLOUT]; /* Skip callout data */ + } + + condcode = code[LINK_SIZE+1]; + + /* Back reference conditions are not supported */ + + if (condcode == OP_CREF) return PCRE_ERROR_DFA_UCOND; + + /* The DEFINE condition is always false */ + + if (condcode == OP_DEF) + { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } + + /* The only supported version of OP_RREF is for the value RREF_ANY, + which means "test if in any recursion". We can't test for specifically + recursed groups. */ + + else if (condcode == OP_RREF) { int value = GET2(code, LINK_SIZE+2); - if (value != 0xffff) return PCRE_ERROR_DFA_UCOND; - if (recursing > 0) { ADD_ACTIVE(state_offset + LINK_SIZE + 4, 0); } - else { ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); } + if (value != RREF_ANY) return PCRE_ERROR_DFA_UCOND; + if (recursing > 0) + { ADD_ACTIVE(state_offset + LINK_SIZE + 4, 0); } + else { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } } /* Otherwise, the condition is an assertion */ @@ -1491,7 +2282,7 @@ (condcode == OP_ASSERT || condcode == OP_ASSERTBACK)) { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); } else - { ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); } + { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } } } break; @@ -1643,9 +2434,9 @@ /* Handle callouts */ case OP_CALLOUT: + rrc = 0; if (pcre_callout != NULL) { - int rrc; pcre_callout_block cb; cb.version = 1; /* Version 1 of the callout block */ cb.callout_number = code[1]; @@ -1660,8 +2451,9 @@ cb.capture_last = -1; cb.callout_data = md->callout_data; if ((rrc = (*pcre_callout)(&cb)) < 0) return rrc; /* Abandon */ - if (rrc == 0) { ADD_ACTIVE(state_offset + 2 + 2*LINK_SIZE, 0); } } + if (rrc == 0) + { ADD_ACTIVE(state_offset + _pcre_OP_lengths[OP_CALLOUT], 0); } break; @@ -1728,7 +2520,7 @@ Arguments: argument_re points to the compiled expression - extra_data points to extra data or is NULL (not currently used) + extra_data points to extra data or is NULL subject points to the subject string length length of subject string (may contain binary zeros) start_offset where to start in the subject string @@ -1744,7 +2536,7 @@ < -1 => some kind of unexpected problem */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, const char *subject, int length, int start_offset, int options, int *offsets, int offsetcount, int *workspace, int wscount) @@ -1834,29 +2626,56 @@ md->moptions = options; md->poptions = re->options; -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ +/* If the BSR option is not set at match time, copy what was set +at compile time. */ + +if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0) + { + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE); +#ifdef BSR_ANYCRLF + else md->moptions |= PCRE_BSR_ANYCRLF; +#endif + } + +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & - PCRE_NEWLINE_CRLF) +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & + PCRE_NEWLINE_BITS) { - default: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; + case 0: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; } -if (newline > 255) +if (newline == -2) { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; } else { - md->nllen = 1; - md->nl[0] = newline; + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } } /* Check a UTF-8 string if required. Unfortunately there's no way of passing @@ -1889,7 +2708,7 @@ used in a loop when finding where to start. */ lcc = md->tables + lcc_offset; -startline = (re->options & PCRE_STARTLINE) != 0; +startline = (re->flags & PCRE_STARTLINE) != 0; firstline = (re->options & PCRE_FIRSTLINE) != 0; /* Set up the first character to match, if available. The first_byte value is @@ -1900,7 +2719,7 @@ if (!anchored) { - if ((re->options & PCRE_FIRSTSET) != 0) + if ((re->flags & PCRE_FIRSTSET) != 0) { first_byte = re->first_byte & 255; if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) @@ -1917,7 +2736,7 @@ /* For anchored or unanchored matches, there may be a "last known required character" set. */ -if ((re->options & PCRE_REQCHSET) != 0) +if ((re->flags & PCRE_REQCHSET) != 0) { req_byte = re->req_byte & 255; req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; @@ -1925,9 +2744,8 @@ } /* Call the main matching function, looping for a non-anchored regex after a -failed match. Unless restarting, optimize by moving to the first match -character if possible, when not anchored. Then unless wanting a partial match, -check for a required later character. */ +failed match. If not restarting, perform certain optimizations at the start of +a match. */ for (;;) { @@ -1937,52 +2755,96 @@ { const uschar *save_end_subject = end_subject; - /* Advance to a unique first char if possible. If firstline is TRUE, the - start of the match is constrained to the first line of a multiline string. - Implement this by temporarily adjusting end_subject so that we stop - scanning at a newline. If the match fails at the newline, later code breaks - this loop. */ + /* If firstline is TRUE, the start of the match is constrained to the first + line of a multiline string. Implement this by temporarily adjusting + end_subject so that we stop scanning at a newline. If the match fails at + the newline, later code breaks this loop. */ if (firstline) { - const uschar *t = current_subject; - while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; + USPTR t = current_subject; +#ifdef SUPPORT_UTF8 + if (utf8) + { + while (t < md->end_subject && !IS_NEWLINE(t)) + { + t++; + while (t < end_subject && (*t & 0xc0) == 0x80) t++; + } + } + else +#endif + while (t < md->end_subject && !IS_NEWLINE(t)) t++; end_subject = t; } - if (first_byte >= 0) + /* There are some optimizations that avoid running the match if a known + starting point is not found, or if a known later character is not present. + However, there is an option that disables these, for testing and for + ensuring that all callouts do actually occur. */ + + if ((options & PCRE_NO_START_OPTIMIZE) == 0) { - if (first_byte_caseless) - while (current_subject < end_subject && - lcc[*current_subject] != first_byte) - current_subject++; - else - while (current_subject < end_subject && *current_subject != first_byte) - current_subject++; - } - /* Or to just after a linebreak for a multiline match if possible */ + /* Advance to a known first byte. */ - else if (startline) - { - if (current_subject > md->start_subject + md->nllen + - start_offset) + if (first_byte >= 0) { - while (current_subject <= end_subject && - !IS_NEWLINE(current_subject - md->nllen)) - current_subject++; + if (first_byte_caseless) + while (current_subject < end_subject && + lcc[*current_subject] != first_byte) + current_subject++; + else + while (current_subject < end_subject && + *current_subject != first_byte) + current_subject++; } - } - /* Or to a non-unique first char after study */ + /* Or to just after a linebreak for a multiline match if possible */ - else if (start_bits != NULL) - { - while (current_subject < end_subject) + else if (startline) + { + if (current_subject > md->start_subject + start_offset) + { +#ifdef SUPPORT_UTF8 + if (utf8) + { + while (current_subject < end_subject && + !WAS_NEWLINE(current_subject)) + { + current_subject++; + while(current_subject < end_subject && + (*current_subject & 0xc0) == 0x80) + current_subject++; + } + } + else +#endif + while (current_subject < end_subject && !WAS_NEWLINE(current_subject)) + current_subject++; + + /* If we have just passed a CR and the newline option is ANY or + ANYCRLF, and we are now at a LF, advance the match position by one + more character. */ + + if (current_subject[-1] == CHAR_CR && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + current_subject < end_subject && + *current_subject == CHAR_NL) + current_subject++; + } + } + + /* Or to a non-unique first char after study */ + + else if (start_bits != NULL) { - register unsigned int c = *current_subject; - if ((start_bits[c/8] & (1 << (c&7))) == 0) current_subject++; - else break; + while (current_subject < end_subject) + { + register unsigned int c = *current_subject; + if ((start_bits[c/8] & (1 << (c&7))) == 0) current_subject++; + else break; + } } } @@ -2004,10 +2866,11 @@ showed up when somebody was matching /^C/ on a 32-megabyte string... so we don't do this when the string is sufficiently long. - ALSO: this processing is disabled when partial matching is requested. - */ + ALSO: this processing is disabled when partial matching is requested, and can + also be explicitly deactivated. */ - if (req_byte >= 0 && + if ((options & PCRE_NO_START_OPTIMIZE) == 0 && + req_byte >= 0 && end_subject - current_subject < REQ_BYTE_MAX && (options & PCRE_PARTIAL) == 0) { @@ -2070,9 +2933,7 @@ /* Advance to the next subject character unless we are at the end of a line and firstline is set. */ - if (firstline && - current_subject <= end_subject - md->nllen && - IS_NEWLINE(current_subject)) break; + if (firstline && IS_NEWLINE(current_subject)) break; current_subject++; if (utf8) { @@ -2080,7 +2941,21 @@ current_subject++; } if (current_subject > end_subject) break; - } + + /* If we have just passed a CR and we are now at a LF, and the pattern does + not contain any explicit matches for \r or \n, and the newline option is CRLF + or ANY or ANYCRLF, advance the match position by one more character. */ + + if (current_subject[-1] == CHAR_CR && + current_subject < end_subject && + *current_subject == CHAR_NL && + (re->flags & PCRE_HASCRORLF) == 0 && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2)) + current_subject++; + + } /* "Bumpalong" loop */ return PCRE_ERROR_NOMATCH; } Modified: freeswitch/trunk/libs/pcre/pcre_exec.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_exec.c (original) +++ freeswitch/trunk/libs/pcre/pcre_exec.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,25 +42,25 @@ pattern matching using an NFA algorithm, trying to mimic Perl as closely as possible. There are also some static supporting functions. */ -#define NLBLOCK md /* The block containing newline information */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + #include "pcre_internal.h" +/* Undefine some potentially clashing cpp symbols */ -/* Structure for building a chain of data that actually lives on the -stack, for holding the values of the subject pointer at the start of each -subpattern, so as to detect when an empty string has been matched by a -subpattern - to break infinite loops. When NO_RECURSE is set, these blocks -are on the heap, not on the stack. */ - -typedef struct eptrblock { - struct eptrblock *epb_prev; - USPTR epb_saved_eptr; -} eptrblock; +#undef min +#undef max /* Flag bits for the match() function */ -#define match_condassert 0x01 /* Called to check a condition assertion */ -#define match_isgroup 0x02 /* Set if start of bracketed group */ +#define match_condassert 0x01 /* Called to check a condition assertion */ +#define match_cbegroup 0x02 /* Could-be-empty unlimited repeat group */ /* Non-error returns from the match() function. Error returns are externally defined PCRE_ERROR_xxx codes, which are all negative. */ @@ -68,6 +68,14 @@ #define MATCH_MATCH 1 #define MATCH_NOMATCH 0 +/* Special internal returns from the match() function. Make them sufficiently +negative to avoid the external error codes. */ + +#define MATCH_COMMIT (-999) +#define MATCH_PRUNE (-998) +#define MATCH_SKIP (-997) +#define MATCH_THEN (-996) + /* Maximum number of ints of offset to save on the stack for recursive calls. If the offset vector is bigger, malloc is used. This should be a multiple of 3, because the offset vector is always a multiple of 3 long. */ @@ -101,7 +109,7 @@ static void pchars(const uschar *p, int length, BOOL is_subject, match_data *md) { -int c; +unsigned int c; if (is_subject && length > md->end_subject - p) length = md->end_subject - p; while (length-- > 0) if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); @@ -150,13 +158,39 @@ if (length > md->end_subject - eptr) return FALSE; -/* Separate the caselesss case for speed */ +/* Separate the caseless case for speed. In UTF-8 mode we can only do this +properly if Unicode properties are supported. Otherwise, we can check only +ASCII characters. */ if ((ims & PCRE_CASELESS) != 0) { +#ifdef SUPPORT_UTF8 +#ifdef SUPPORT_UCP + if (md->utf8) + { + USPTR endptr = eptr + length; + while (eptr < endptr) + { + int c, d; + GETCHARINC(c, eptr); + GETCHARINC(d, p); + if (c != d && c != UCD_OTHERCASE(d)) return FALSE; + } + } + else +#endif +#endif + + /* The same code works when not in UTF-8 mode and in UTF-8 mode when there + is no UCP support. */ + while (length-- > 0) - if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; + { if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; } } + +/* In the caseful case, we can just compare the bytes, whether or not we +are in UTF-8 mode. */ + else { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } @@ -186,20 +220,45 @@ obtained from malloc() instead instead of on the stack. Macros are used to achieve this so that the actual code doesn't look very different to what it always used to. + +The original heap-recursive code used longjmp(). However, it seems that this +can be very slow on some operating systems. Following a suggestion from Stan +Switzer, the use of longjmp() has been abolished, at the cost of having to +provide a unique number for each call to RMATCH. There is no way of generating +a sequence of numbers at compile time in C. I have given them names, to make +them stand out more clearly. + +Crude tests on x86 Linux show a small speedup of around 5-8%. However, on +FreeBSD, avoiding longjmp() more than halves the time taken to run the standard +tests. Furthermore, not using longjmp() means that local dynamic variables +don't have indeterminate values; this has meant that the frame size can be +reduced because the result can be "passed back" by straight setting of the +variable instead of being passed in the frame. **************************************************************************** ***************************************************************************/ +/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN +below must be updated in sync. */ + +enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, + RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, + RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, + RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, + RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, + RM51, RM52, RM53, RM54 }; /* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. */ +versions and production versions. Note that the "rw" argument of RMATCH isn't +actuall used in this definition. */ #ifndef NO_RECURSE #define REGISTER register + #ifdef PCRE_DEBUG -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ { \ printf("match() called in line %d\n", __LINE__); \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1); \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \ printf("to line %d\n", __LINE__); \ } #define RRETURN(ra) \ @@ -208,43 +267,38 @@ return ra; \ } #else -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1) +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1) #define RRETURN(ra) return ra #endif #else -/* These versions of the macros manage a private stack on the heap. Note -that the rd argument of RMATCH isn't actually used. It's the md argument of -match(), which never changes. */ +/* These versions of the macros manage a private stack on the heap. Note that +the "rd" argument of RMATCH isn't actually used in this definition. It's the md +argument of match(), which never changes. */ #define REGISTER -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg)\ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw)\ {\ heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - if (setjmp(frame->Xwhere) == 0)\ - {\ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - }\ - else\ - {\ - DPRINTF(("longjumped back to line %d\n", __LINE__));\ - frame = md->thisframe;\ - rx = frame->Xresult;\ - }\ + frame->Xwhere = rw; \ + newframe->Xeptr = ra;\ + newframe->Xecode = rb;\ + newframe->Xmstart = mstart;\ + newframe->Xoffset_top = rc;\ + newframe->Xims = re;\ + newframe->Xeptrb = rf;\ + newframe->Xflags = rg;\ + newframe->Xrdepth = frame->Xrdepth + 1;\ + newframe->Xprevframe = frame;\ + frame = newframe;\ + DPRINTF(("restarting from line %d\n", __LINE__));\ + goto HEAP_RECURSE;\ + L_##rw:\ + DPRINTF(("jumped back to line %d\n", __LINE__));\ } #define RRETURN(ra)\ @@ -254,9 +308,8 @@ (pcre_stack_free)(newframe);\ if (frame != NULL)\ {\ - frame->Xresult = ra;\ - md->thisframe = frame;\ - longjmp(frame->Xwhere, 1);\ + rrc = ra;\ + goto HEAP_RETURN;\ }\ return ra;\ } @@ -269,8 +322,9 @@ /* Function arguments that may change */ - const uschar *Xeptr; + USPTR Xeptr; const uschar *Xecode; + USPTR Xmstart; int Xoffset_top; long int Xims; eptrblock *Xeptrb; @@ -279,19 +333,20 @@ /* Function local variables */ - const uschar *Xcallpat; - const uschar *Xcharptr; - const uschar *Xdata; - const uschar *Xnext; - const uschar *Xpp; - const uschar *Xprev; - const uschar *Xsaved_eptr; + USPTR Xcallpat; +#ifdef SUPPORT_UTF8 + USPTR Xcharptr; +#endif + USPTR Xdata; + USPTR Xnext; + USPTR Xpp; + USPTR Xprev; + USPTR Xsaved_eptr; recursion_info Xnew_recursive; BOOL Xcur_is_word; BOOL Xcondition; - BOOL Xminimize; BOOL Xprev_is_word; unsigned long int Xoriginal_ims; @@ -303,11 +358,13 @@ int Xprop_category; int Xprop_chartype; int Xprop_script; - int *Xprop_test_variable; + int Xoclength; + uschar Xocchars[8]; #endif + int Xcodelink; int Xctype; - int Xfc; + unsigned int Xfc; int Xfi; int Xlength; int Xmax; @@ -321,10 +378,9 @@ eptrblock Xnewptrb; - /* Place to pass back result, and where to jump back to */ + /* Where to jump back to */ - int Xresult; - jmp_buf Xwhere; + int Xwhere; } heapframe; @@ -340,10 +396,7 @@ * Match from current position * *************************************************/ -/* On entry ecode points to the first opcode, and eptr to the first character -in the subject string, while eptrb holds the value of eptr at the start of the -last bracketed group - used for breaking infinite loops matching zero-length -strings. This function is called recursively in many circumstances. Whenever it +/* This function is called recursively in many circumstances. Whenever it returns a negative (error) response, the outer incarnation must also return the same response. @@ -353,8 +406,10 @@ made performance worse. Arguments: - eptr pointer in subject - ecode position in code + eptr pointer to current character in subject + ecode pointer to current position in compiled code + mstart pointer to the current match start position (can be modified + by encountering \K) offset_top current top pointer md pointer to "static" info for the match ims current /i, /m, and /s options @@ -362,7 +417,8 @@ brackets - for testing for empty matches flags can contain match_condassert - this is an assertion condition - match_isgroup - this is the start of a bracketed group + match_cbegroup - this is the start of an unlimited repeat + group that can match an empty string rdepth the recursion depth Returns: MATCH_MATCH if matched ) these values are >= 0 @@ -372,19 +428,22 @@ */ static int -match(REGISTER USPTR eptr, REGISTER const uschar *ecode, +match(REGISTER USPTR eptr, REGISTER const uschar *ecode, USPTR mstart, int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, int flags, unsigned int rdepth) { /* These variables do not need to be preserved over recursion in this function, -so they can be ordinary variables in all cases. Mark them with "register" -because they are used a lot in loops. */ +so they can be ordinary variables in all cases. Mark some of them with +"register" because they are used a lot in loops. */ register int rrc; /* Returns from recursive calls */ register int i; /* Used for loops not involving calls to RMATCH() */ -register unsigned int c; /* Character values not kept over RMATCH() calls */ +register unsigned int c; /* Character values not kept over RMATCH() calls */ register BOOL utf8; /* Local copy of UTF-8 flag for speed */ +BOOL minimize, possessive; /* Quantifier options */ +int condcode; + /* When recursion is not being used, all "local" variables that have to be preserved over calls to RMATCH() are part of a "frame" which is obtained from heap storage. Set up the top-level frame here; others are obtained from the @@ -398,6 +457,7 @@ frame->Xeptr = eptr; frame->Xecode = ecode; +frame->Xmstart = mstart; frame->Xoffset_top = offset_top; frame->Xims = ims; frame->Xeptrb = eptrb; @@ -412,6 +472,7 @@ #define eptr frame->Xeptr #define ecode frame->Xecode +#define mstart frame->Xmstart #define offset_top frame->Xoffset_top #define ims frame->Xims #define eptrb frame->Xeptrb @@ -424,6 +485,7 @@ #define charptr frame->Xcharptr #endif #define callpat frame->Xcallpat +#define codelink frame->Xcodelink #define data frame->Xdata #define next frame->Xnext #define pp frame->Xpp @@ -434,7 +496,6 @@ #define cur_is_word frame->Xcur_is_word #define condition frame->Xcondition -#define minimize frame->Xminimize #define prev_is_word frame->Xprev_is_word #define original_ims frame->Xoriginal_ims @@ -446,7 +507,8 @@ #define prop_category frame->Xprop_category #define prop_chartype frame->Xprop_chartype #define prop_script frame->Xprop_script -#define prop_test_variable frame->Xprop_test_variable +#define oclength frame->Xoclength +#define occhars frame->Xocchars #endif #define ctype frame->Xctype @@ -470,7 +532,7 @@ get preserved during recursion in the normal way. In this environment, fi and i, and fc and c, can be the same variables. */ -#else +#else /* NO_RECURSE not defined */ #define fi i #define fc c @@ -489,7 +551,6 @@ /* that do not have to be preserved over */ BOOL cur_is_word; /* a recursive call to RMATCH(). */ BOOL condition; -BOOL minimize; BOOL prev_is_word; unsigned long int original_ims; @@ -501,9 +562,11 @@ int prop_category; int prop_chartype; int prop_script; -int *prop_test_variable; +int oclength; +uschar occhars[8]; #endif +int codelink; int ctype; int length; int max; @@ -516,7 +579,7 @@ int stacksave[REC_STACK_SAVE_MAX]; eptrblock newptrb; -#endif +#endif /* NO_RECURSE */ /* These statements are here to stop the compiler complaining about unitialized variables. */ @@ -524,9 +587,9 @@ #ifdef SUPPORT_UCP prop_value = 0; prop_fail_result = 0; -prop_test_variable = NULL; #endif + /* This label is used for tail recursion, which is used in a few cases even when NO_RECURSE is not defined, in order to reduce the amount of stack that is used. Thanks to Ian Taylor for noticing this possibility and sending the @@ -542,6 +605,12 @@ complicated macro. It has to be used in one particular way. This shouldn't, however, impact performance when true recursion is being used. */ +#ifdef SUPPORT_UTF8 +utf8 = md->utf8; /* Local copy of the flag */ +#else +utf8 = FALSE; +#endif + /* First check that we haven't called match() too many times, or that we haven't exceeded the recursive call limit. */ @@ -550,66 +619,89 @@ original_ims = ims; /* Save for resetting on ')' */ -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif - -/* At the start of a bracketed group, add the current subject pointer to the -stack of such pointers, to be re-instated at the end of the group when we hit -the closing ket. When match() is called in other circumstances, we don't add to -this stack. */ +/* At the start of a group with an unlimited repeat that may match an empty +string, the match_cbegroup flag is set. When this is the case, add the current +subject pointer to the chain of such remembered pointers, to be checked when we +hit the closing ket, in order to break infinite loops that match no characters. +When match() is called in other circumstances, don't add to the chain. The +match_cbegroup flag must NOT be used with tail recursion, because the memory +block that is used is on the stack, so a new one may be required for each +match(). */ -if ((flags & match_isgroup) != 0) +if ((flags & match_cbegroup) != 0) { - newptrb.epb_prev = eptrb; newptrb.epb_saved_eptr = eptr; + newptrb.epb_prev = eptrb; eptrb = &newptrb; } -/* Now start processing the operations. */ +/* Now start processing the opcodes. */ for (;;) { + minimize = possessive = FALSE; op = *ecode; - minimize = FALSE; /* For partial matching, remember if we ever hit the end of the subject after matching at least one subject character. */ if (md->partial && eptr >= md->end_subject && - eptr > md->start_match) + eptr > mstart) md->hitend = TRUE; - /* Opening capturing bracket. If there is space in the offset vector, save - the current subject position in the working slot at the top of the vector. We - mustn't change the current values of the data slot, because they may be set - from a previous iteration of this group, and be referred to by a reference - inside the group. - - If the bracket fails to match, we need to restore this value and also the - values of the final offsets, in case they were set by a previous iteration of - the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were a - non-capturing bracket. Don't worry about setting the flag for the error case - here; that is handled in the code for KET. */ - - if (op > OP_BRA) + switch(op) { - number = op - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out the - number from a dummy opcode at the start. */ + case OP_FAIL: + RRETURN(MATCH_NOMATCH); - if (number > EXTRACT_BASIC_MAX) - number = GET2(ecode, 2+LINK_SIZE); + case OP_PRUNE: + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM51); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_PRUNE); + + case OP_COMMIT: + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM52); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_COMMIT); + + case OP_SKIP: + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM53); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->start_match_ptr = eptr; /* Pass back current position */ + RRETURN(MATCH_SKIP); + + case OP_THEN: + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM54); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_THEN); + + /* Handle a capturing bracket. If there is space in the offset vector, save + the current subject position in the working slot at the top of the vector. + We mustn't change the current values of the data slot, because they may be + set from a previous iteration of this group, and be referred to by a + reference inside the group. + + If the bracket fails to match, we need to restore this value and also the + values of the final offsets, in case they were set by a previous iteration + of the same bracket. + + If there isn't enough space in the offset vector, treat this as if it were + a non-capturing bracket. Don't worry about setting the flag for the error + case here; that is handled in the code for KET. */ + + case OP_CBRA: + case OP_SCBRA: + number = GET2(ecode, 1+LINK_SIZE); offset = number << 1; #ifdef PCRE_DEBUG - printf("start bracket %d subject=", number); + printf("start bracket %d\n", number); + printf("subject="); pchars(eptr, 16, TRUE, md); printf("\n"); #endif @@ -624,11 +716,12 @@ DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); md->offset_vector[md->offset_end - number] = eptr - md->start_subject; + flags = (op == OP_SCBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM1); + if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); md->capture_last = save_capture_last; ecode += GET(ecode, 1); } @@ -643,40 +736,51 @@ RRETURN(MATCH_NOMATCH); } - /* Insufficient room for saving captured contents */ - - else op = OP_BRA; - } - - /* Other types of node can be handled by a switch */ + /* FALL THROUGH ... Insufficient room for saving captured contents. Treat + as a non-capturing bracket. */ - switch(op) - { - case OP_BRA: /* Non-capturing bracket: optimized */ - DPRINTF(("start bracket 0\n")); + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* Loop for all the alternatives */ + DPRINTF(("insufficient capture room: treat as non-capturing\n")); + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + + /* Non-capturing bracket. Loop for all the alternatives. When we get to the + final alternative within the brackets, we would return the result of a + recursive call to match() whatever happened. We can reduce stack usage by + turning this into a tail recursion, except in the case when match_cbegroup + is set.*/ + + case OP_BRA: + case OP_SBRA: + DPRINTF(("start non-capturing bracket\n")); + flags = (op >= OP_SBRA)? match_cbegroup : 0; for (;;) { - /* When we get to the final alternative within the brackets, we would - return the result of a recursive call to match() whatever happened. We - can reduce stack usage by turning this into a tail recursion. */ - - if (ecode[GET(ecode, 1)] != OP_ALT) - { - ecode += 1 + LINK_SIZE; - flags = match_isgroup; - DPRINTF(("bracket 0 tail recursion\n")); - goto TAIL_RECURSE; - } + if (ecode[GET(ecode, 1)] != OP_ALT) /* Final alternative */ + { + if (flags == 0) /* Not a possibly empty group */ + { + ecode += _pcre_OP_lengths[*ecode]; + DPRINTF(("bracket 0 tail recursion\n")); + goto TAIL_RECURSE; + } + + /* Possibly empty group; can't use tail recursion. */ + + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, + eptrb, flags, RM48); + RRETURN(rrc); + } /* For non-final alternatives, continue the loop for a NOMATCH result; otherwise return. */ - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, + eptrb, flags, RM2); + if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); ecode += GET(ecode, 1); } /* Control never reaches here. */ @@ -688,55 +792,116 @@ obeyed, we can use tail recursion to avoid using another stack frame. */ case OP_COND: - if (ecode[LINK_SIZE+1] == OP_CREF) /* Condition extract or recurse test */ + case OP_SCOND: + codelink= GET(ecode, 1); + + /* Because of the way auto-callout works during compile, a callout item is + inserted between OP_COND and an assertion condition. */ + + if (ecode[LINK_SIZE+1] == OP_CALLOUT) + { + if (pcre_callout != NULL) + { + pcre_callout_block cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = ecode[LINK_SIZE+2]; + cb.offset_vector = md->offset_vector; + cb.subject = (PCRE_SPTR)md->start_subject; + cb.subject_length = md->end_subject - md->start_subject; + cb.start_match = mstart - md->start_subject; + cb.current_position = eptr - md->start_subject; + cb.pattern_position = GET(ecode, LINK_SIZE + 3); + cb.next_item_length = GET(ecode, 3 + 2*LINK_SIZE); + cb.capture_top = offset_top/2; + cb.capture_last = md->capture_last; + cb.callout_data = md->callout_data; + if ((rrc = (*pcre_callout)(&cb)) > 0) RRETURN(MATCH_NOMATCH); + if (rrc < 0) RRETURN(rrc); + } + ecode += _pcre_OP_lengths[OP_CALLOUT]; + } + + condcode = ecode[LINK_SIZE+1]; + + /* Now see what the actual condition is */ + + if (condcode == OP_RREF) /* Recursion test */ + { + offset = GET2(ecode, LINK_SIZE + 2); /* Recursion group number*/ + condition = md->recursive != NULL && + (offset == RREF_ANY || offset == md->recursive->group_num); + ecode += condition? 3 : GET(ecode, 1); + } + + else if (condcode == OP_CREF) /* Group used test */ { offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ - condition = (offset == CREF_RECURSE * 2)? - (md->recursive != NULL) : - (offset < offset_top && md->offset_vector[offset] >= 0); - ecode += condition? (LINK_SIZE + 4) : (LINK_SIZE + 1 + GET(ecode, 1)); - flags = match_isgroup; - goto TAIL_RECURSE; + condition = offset < offset_top && md->offset_vector[offset] >= 0; + ecode += condition? 3 : GET(ecode, 1); + } + + else if (condcode == OP_DEF) /* DEFINE - always false */ + { + condition = FALSE; + ecode += GET(ecode, 1); } /* The condition is an assertion. Call match() to evaluate it - setting - the final argument TRUE causes it to stop at the end of an assertion. */ + the final argument match_condassert causes it to stop at the end of an + assertion. */ else { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert | match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_condassert, RM3); if (rrc == MATCH_MATCH) { - ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE+2); + condition = TRUE; + ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); while (*ecode == OP_ALT) ecode += GET(ecode, 1); } - else if (rrc != MATCH_NOMATCH) + else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) { RRETURN(rrc); /* Need braces because of following else */ } - else ecode += GET(ecode, 1); + else + { + condition = FALSE; + ecode += codelink; + } + } - /* We are now at the branch that is to be obeyed. As there is only one, - we can use tail recursion to avoid using another stack frame. */ + /* We are now at the branch that is to be obeyed. As there is only one, + we can use tail recursion to avoid using another stack frame, except when + match_cbegroup is required for an unlimited repeat of a possibly empty + group. If the second alternative doesn't exist, we can just plough on. */ + if (condition || *ecode == OP_ALT) + { + ecode += 1 + LINK_SIZE; + if (op == OP_SCOND) /* Possibly empty group */ + { + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, match_cbegroup, RM49); + RRETURN(rrc); + } + else /* Group must match something */ + { + flags = 0; + goto TAIL_RECURSE; + } + } + else /* Condition false & no alternative */ + { ecode += 1 + LINK_SIZE; - flags = match_isgroup; - goto TAIL_RECURSE; } - /* Control never reaches here */ - - /* Skip over conditional reference or large extraction number data if - encountered. */ - - case OP_CREF: - case OP_BRANUMBER: - ecode += 3; break; - /* End of the pattern. If we are in a recursion, we should restore the - offsets appropriately and continue from after the call. */ + /* End of the pattern, either real or forced. If we are in a top-level + recursion, we should restore the offsets appropriately and continue from + after the call. */ + + case OP_ACCEPT: case OP_END: if (md->recursive != NULL && md->recursive->group_num == 0) { @@ -745,7 +910,7 @@ md->recursive = rec->prevrec; memmove(md->offset_vector, rec->offset_save, rec->saved_max * sizeof(int)); - md->start_match = rec->save_start; + mstart = rec->save_start; ims = original_ims; ecode = rec->after_call; break; @@ -754,9 +919,10 @@ /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty string - backtracking will then try other alternatives, if any. */ - if (md->notempty && eptr == md->start_match) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ + if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); + md->end_match_ptr = eptr; /* Record where we ended */ + md->end_offset_top = offset_top; /* and how many extracts were taken */ + md->start_match_ptr = mstart; /* and the start (\K can modify) */ RRETURN(MATCH_MATCH); /* Change option settings */ @@ -777,10 +943,10 @@ case OP_ASSERTBACK: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM4); if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); ecode += GET(ecode, 1); } while (*ecode == OP_ALT); @@ -804,10 +970,10 @@ case OP_ASSERTBACK_NOT: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM5); if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); ecode += GET(ecode,1); } while (*ecode == OP_ALT); @@ -826,12 +992,12 @@ #ifdef SUPPORT_UTF8 if (utf8) { - c = GET(ecode,1); - for (i = 0; i < c; i++) + i = GET(ecode, 1); + while (i-- > 0) { eptr--; if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - BACKCHAR(eptr) + BACKCHAR(eptr); } } else @@ -840,7 +1006,7 @@ /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ { - eptr -= GET(ecode,1); + eptr -= GET(ecode, 1); if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); } @@ -862,7 +1028,7 @@ cb.offset_vector = md->offset_vector; cb.subject = (PCRE_SPTR)md->start_subject; cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = md->start_match - md->start_subject; + cb.start_match = mstart - md->start_subject; cb.current_position = eptr - md->start_subject; cb.pattern_position = GET(ecode, 2); cb.next_item_length = GET(ecode, 2 + LINK_SIZE); @@ -897,13 +1063,8 @@ case OP_RECURSE: { callpat = md->start_code + GET(ecode, 1); - new_recursive.group_num = *callpat - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (new_recursive.group_num > EXTRACT_BASIC_MAX) - new_recursive.group_num = GET2(callpat, 2+LINK_SIZE); + new_recursive.group_num = (callpat == md->start_code)? 0 : + GET2(callpat, 1 + LINK_SIZE); /* Add to "recursing stack" */ @@ -929,17 +1090,18 @@ memcpy(new_recursive.offset_save, md->offset_vector, new_recursive.saved_max * sizeof(int)); - new_recursive.save_start = md->start_match; - md->start_match = eptr; + new_recursive.save_start = mstart; + mstart = eptr; /* OK, now we can do the recursion. For each top-level alternative we restore the offset and recursion data. */ DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); + flags = (*callpat >= OP_SBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, callpat + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); + RMATCH(eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, + md, ims, eptrb, flags, RM6); if (rrc == MATCH_MATCH) { DPRINTF(("Recursion matched\n")); @@ -948,9 +1110,11 @@ (pcre_free)(new_recursive.offset_save); RRETURN(MATCH_MATCH); } - else if (rrc != MATCH_NOMATCH) + else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) { DPRINTF(("Recursion gave error %d\n", rrc)); + if (new_recursive.offset_save != stacksave) + (pcre_free)(new_recursive.offset_save); RRETURN(rrc); } @@ -982,10 +1146,9 @@ do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7); if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); ecode += GET(ecode,1); } while (*ecode == OP_ALT); @@ -997,7 +1160,7 @@ /* Continue as from after the assertion, updating the offsets high water mark, since extracts may have been taken. */ - do ecode += GET(ecode,1); while (*ecode == OP_ALT); + do ecode += GET(ecode, 1); while (*ecode == OP_ALT); offset_top = md->end_offset_top; eptr = md->end_match_ptr; @@ -1028,15 +1191,15 @@ if (*ecode == OP_KETRMIN) { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM8); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode = prev; - flags = match_isgroup; + flags = 0; goto TAIL_RECURSE; } else /* OP_KETRMAX */ { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); + RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; flags = 0; @@ -1051,47 +1214,61 @@ do ecode += GET(ecode,1); while (*ecode == OP_ALT); break; - /* BRAZERO and BRAMINZERO occur just before a bracket group, indicating - that it may occur zero times. It may repeat infinitely, or not at all - - i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper - repeat limits are compiled as a number of copies, with the optional ones - preceded by BRAZERO or BRAMINZERO. */ + /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group, + indicating that it may occur zero times. It may repeat infinitely, or not + at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets + with fixed upper repeat limits are compiled as a number of copies, with the + optional ones preceded by BRAZERO or BRAMINZERO. */ case OP_BRAZERO: { next = ecode+1; - RMATCH(rrc, eptr, next, offset_top, md, ims, eptrb, match_isgroup); + RMATCH(eptr, next, offset_top, md, ims, eptrb, 0, RM10); if (rrc != MATCH_NOMATCH) RRETURN(rrc); do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1+LINK_SIZE; + ecode = next + 1 + LINK_SIZE; } break; case OP_BRAMINZERO: { next = ecode+1; - do next += GET(next,1); while (*next == OP_ALT); - RMATCH(rrc, eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); + do next += GET(next, 1); while (*next == OP_ALT); + RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, RM11); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode++; } break; - /* End of a group, repeated or non-repeating. If we are at the end of - an assertion "group", stop matching and return MATCH_MATCH, but record the - current high water mark for use by positive assertions. Do this also - for the "once" (not-backup up) groups. */ + case OP_SKIPZERO: + { + next = ecode+1; + do next += GET(next,1); while (*next == OP_ALT); + ecode = next + 1 + LINK_SIZE; + } + break; + + /* End of a group, repeated or non-repeating. */ case OP_KET: case OP_KETRMIN: case OP_KETRMAX: prev = ecode - GET(ecode, 1); - saved_eptr = eptrb->epb_saved_eptr; - /* Back up the stack of bracket start pointers. */ + /* If this was a group that remembered the subject start, in order to break + infinite repeats of empty string matches, retrieve the subject start from + the chain. Otherwise, set it NULL. */ + + if (*prev >= OP_SBRA) + { + saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ + eptrb = eptrb->epb_prev; /* Backup to previous group */ + } + else saved_eptr = NULL; - eptrb = eptrb->epb_prev; + /* If we are at the end of an assertion group, stop matching and return + MATCH_MATCH, but record the current high water mark for use by positive + assertions. Do this also for the "once" (atomic) groups. */ if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || @@ -1102,18 +1279,15 @@ RRETURN(MATCH_MATCH); } - /* In all other cases except a conditional group we have to check the - group number back at the start and if necessary complete handling an - extraction by setting the offsets and bumping the high water mark. */ + /* For capturing groups we have to check the group number back at the start + and if necessary complete handling an extraction by setting the offsets and + bumping the high water mark. Note that whole-pattern recursion is coded as + a recurse into group 0, so it won't be picked up here. Instead, we catch it + when the OP_END is reached. Other recursion is handled here. */ - if (*prev != OP_COND) + if (*prev == OP_CBRA || *prev == OP_SCBRA) { - number = *prev - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (number > EXTRACT_BASIC_MAX) number = GET2(prev, 2+LINK_SIZE); + number = GET2(prev, 1+LINK_SIZE); offset = number << 1; #ifdef PCRE_DEBUG @@ -1121,42 +1295,34 @@ printf("\n"); #endif - /* Test for a numbered group. This includes groups called as a result - of recursion. Note that whole-pattern recursion is coded as a recurse - into group 0, so it won't be picked up here. Instead, we catch it when - the OP_END is reached. */ - - if (number > 0) + md->capture_last = number; + if (offset >= md->offset_max) md->offset_overflow = TRUE; else { - md->capture_last = number; - if (offset >= md->offset_max) md->offset_overflow = TRUE; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - - /* Handle a recursively called group. Restore the offsets - appropriately and continue from after the call. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - recursion_info *rec = md->recursive; - DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); - md->recursive = rec->prevrec; - md->start_match = rec->save_start; - memcpy(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - ecode = rec->after_call; - ims = original_ims; - break; - } + md->offset_vector[offset] = + md->offset_vector[md->offset_end - number]; + md->offset_vector[offset+1] = eptr - md->start_subject; + if (offset_top <= offset) offset_top = offset + 2; + } + + /* Handle a recursively called group. Restore the offsets + appropriately and continue from after the call. */ + + if (md->recursive != NULL && md->recursive->group_num == number) + { + recursion_info *rec = md->recursive; + DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); + md->recursive = rec->prevrec; + mstart = rec->save_start; + memcpy(md->offset_vector, rec->offset_save, + rec->saved_max * sizeof(int)); + ecode = rec->after_call; + ims = original_ims; + break; } } - /* Reset the value of the ims flags, in case they got changed during - the group. */ + /* For both capturing and non-capturing groups, reset the value of the ims + flags, in case they got changed during the group. */ ims = original_ims; DPRINTF(("ims reset to %02lx\n", ims)); @@ -1175,19 +1341,26 @@ /* The repeating kets try the rest of the pattern or restart from the preceding bracket, in the appropriate order. In the second case, we can use - tail recursion to avoid using another stack frame. */ + tail recursion to avoid using another stack frame, unless we have an + unlimited repeat of a group that can match an empty string. */ + + flags = (*prev >= OP_SBRA)? match_cbegroup : 0; if (*ecode == OP_KETRMIN) { - RMATCH(rrc, eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM12); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (flags != 0) /* Could match an empty string */ + { + RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM50); + RRETURN(rrc); + } ecode = prev; - flags = match_isgroup; goto TAIL_RECURSE; } else /* OP_KETRMAX */ { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); + RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; flags = 0; @@ -1202,9 +1375,7 @@ if ((ims & PCRE_MULTILINE) != 0) { if (eptr != md->start_subject && - (eptr == md->end_subject || - eptr < md->start_subject + md->nllen || - !IS_NEWLINE(eptr - md->nllen))) + (eptr == md->end_subject || !WAS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1225,6 +1396,13 @@ ecode++; break; + /* Reset the start of match point */ + + case OP_SET_SOM: + mstart = eptr; + ecode++; + break; + /* Assert before internal newline if multiline, or before a terminating newline unless endonly is set, else end of subject unless noteol is set. */ @@ -1244,7 +1422,7 @@ if (!md->endonly) { if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1263,7 +1441,7 @@ case OP_EODN: if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) RRETURN(MATCH_NOMATCH); ecode++; break; @@ -1283,7 +1461,7 @@ { if (eptr == md->start_subject) prev_is_word = FALSE; else { - const uschar *lastptr = eptr - 1; + USPTR lastptr = eptr - 1; while((*lastptr & 0xc0) == 0x80) lastptr--; GETCHAR(c, lastptr); prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; @@ -1317,14 +1495,12 @@ /* Match a single character type; inline for speed */ case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - } + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); + /* Fall through */ + + case OP_ALLANY: if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (utf8) - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + if (utf8) while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; ecode++; break; @@ -1414,6 +1590,126 @@ ecode++; break; + case OP_ANYNL: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + + case 0x000a: + break; + + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + ecode++; + break; + + case OP_NOT_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + ecode++; + break; + + case OP_NOT_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + ecode++; + break; + #ifdef SUPPORT_UCP /* Check the next character by Unicode property. We will get here only if the support is in the binary; otherwise a compile-time error occurs. */ @@ -1423,8 +1719,7 @@ if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINCTEST(c, eptr); { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record *prop = GET_UCD(c); switch(ecode[1]) { @@ -1433,30 +1728,29 @@ break; case PT_LAMP: - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == (op == OP_NOTPROP)) + if ((prop->chartype == ucp_Lu || + prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt) == (op == OP_NOTPROP)) RRETURN(MATCH_NOMATCH); break; case PT_GC: - if ((ecode[2] != category) == (op == OP_PROP)) + if ((ecode[2] != _pcre_ucp_gentype[prop->chartype]) == (op == OP_PROP)) RRETURN(MATCH_NOMATCH); break; case PT_PC: - if ((ecode[2] != chartype) == (op == OP_PROP)) + if ((ecode[2] != prop->chartype) == (op == OP_PROP)) RRETURN(MATCH_NOMATCH); break; case PT_SC: - if ((ecode[2] != script) == (op == OP_PROP)) + if ((ecode[2] != prop->script) == (op == OP_PROP)) RRETURN(MATCH_NOMATCH); break; default: RRETURN(PCRE_ERROR_INTERNAL); - break; } ecode += 3; @@ -1470,8 +1764,7 @@ if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINCTEST(c, eptr); { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); + int category = UCD_CATEGORY(c); if (category == ucp_M) RRETURN(MATCH_NOMATCH); while (eptr < md->end_subject) { @@ -1480,7 +1773,7 @@ { GETCHARLEN(c, eptr, len); } - category = _pcre_ucp_findprop(c, &chartype, &script); + category = UCD_CATEGORY(c); if (category != ucp_M) break; eptr += len; } @@ -1501,16 +1794,25 @@ case OP_REF: { offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - ecode += 3; /* Advance past item */ + ecode += 3; + + /* If the reference is unset, there are two possibilities: + + (a) In the default, Perl-compatible state, set the length to be longer + than the amount of subject left; this ensures that every attempt at a + match fails. We can't just fail here, because of the possibility of + quantifiers with zero minima. + + (b) If the JavaScript compatibility flag is set, set the length to zero + so that the back reference matches an empty string. - /* If the reference is unset, set the length to be longer than the amount - of subject left; this ensures that every attempt at a match fails. We - can't just fail here, because of the possibility of quantifiers with zero - minima. */ - - length = (offset >= offset_top || md->offset_vector[offset] < 0)? - md->end_subject - eptr + 1 : - md->offset_vector[offset+1] - md->offset_vector[offset]; + Otherwise, set the length to the length of what was matched by the + referenced subpattern. */ + + if (offset >= offset_top || md->offset_vector[offset] < 0) + length = (md->jscript_compat)? 0 : md->end_subject - eptr + 1; + else + length = md->offset_vector[offset+1] - md->offset_vector[offset]; /* Set up for repetition, or handle the non-repeated case */ @@ -1570,7 +1872,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM14); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || !match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); @@ -1591,7 +1893,7 @@ } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM15); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr -= length; } @@ -1696,7 +1998,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM16); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -1716,7 +2018,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM17); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); c = *eptr++; @@ -1753,7 +2055,7 @@ } for (;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM18); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -1772,7 +2074,7 @@ } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM19); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -1785,7 +2087,8 @@ /* Match an extended character class. This opcode is encountered only - in UTF-8 mode, because that's the only time it is compiled. */ + when UTF-8 mode mode is supported. Nevertheless, we may not be in UTF-8 + mode, because Unicode properties are supported in non-UTF-8 mode. */ #ifdef SUPPORT_UTF8 case OP_XCLASS: @@ -1827,7 +2130,7 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); } @@ -1843,10 +2146,10 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM20); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); } /* Control never gets here */ @@ -1861,16 +2164,16 @@ { int len = 1; if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); + GETCHARLENTEST(c, eptr, len); if (!_pcre_xclass(c, data)) break; eptr += len; } for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr) + if (utf8) BACKCHAR(eptr); } RRETURN(MATCH_NOMATCH); } @@ -1926,7 +2229,7 @@ else { - int dc; + unsigned int dc; GETCHARINC(dc, eptr); ecode += length; @@ -1936,7 +2239,7 @@ if (fc != dc) { #ifdef SUPPORT_UCP - if (dc != _pcre_ucp_othercase(fc)) + if (dc != UCD_OTHERCASE(fc)) #endif RRETURN(MATCH_NOMATCH); } @@ -1953,13 +2256,17 @@ } break; - /* Match a single character repeatedly; different opcodes share code. */ + /* Match a single character repeatedly. */ case OP_EXACT: min = max = GET2(ecode, 1); ecode += 3; goto REPEATCHAR; + case OP_POSUPTO: + possessive = TRUE; + /* Fall through */ + case OP_UPTO: case OP_MINUPTO: min = 0; @@ -1968,6 +2275,27 @@ ecode += 3; goto REPEATCHAR; + case OP_POSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATCHAR; + case OP_STAR: case OP_MINSTAR: case OP_PLUS: @@ -1999,20 +2327,18 @@ if (length > 1) { - int oclength = 0; - uschar occhars[8]; - #ifdef SUPPORT_UCP - int othercase; + unsigned int othercase; if ((ims & PCRE_CASELESS) != 0 && - (othercase = _pcre_ucp_othercase(fc)) >= 0 && - othercase >= 0) + (othercase = UCD_OTHERCASE(fc)) != fc) oclength = _pcre_ord2utf8(othercase, occhars); + else oclength = 0; #endif /* SUPPORT_UCP */ for (i = 1; i <= min; i++) { if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2020,6 +2346,9 @@ if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN(MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } if (min == max) continue; @@ -2028,10 +2357,11 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM22); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2039,30 +2369,45 @@ if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN (MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } /* Control never gets here */ } - else + + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) { if (eptr > md->end_subject - length) break; if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP else if (oclength == 0) break; else { if (memcmp(eptr, occhars, oclength) != 0) break; eptr += oclength; } +#else /* without SUPPORT_UCP */ + else break; +#endif /* SUPPORT_UCP */ } - while (eptr >= pp) + + if (possessive) continue; + for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM23); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr == pp) RRETURN(MATCH_NOMATCH); +#ifdef SUPPORT_UCP + eptr--; + BACKCHAR(eptr); +#else /* without SUPPORT_UCP */ eptr -= length; +#endif /* SUPPORT_UCP */ } - RRETURN(MATCH_NOMATCH); } /* Control never gets here */ } @@ -2102,7 +2447,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM24); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != md->lcc[*eptr++]) @@ -2110,7 +2455,7 @@ } /* Control never gets here */ } - else + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) @@ -2118,9 +2463,10 @@ if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM25); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2139,14 +2485,14 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM26); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != *eptr++) RRETURN(MATCH_NOMATCH); } /* Control never gets here */ } - else + else /* Maximize */ { pp = eptr; for (i = min; i < max; i++) @@ -2154,9 +2500,10 @@ if (eptr >= md->end_subject || fc != *eptr) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM27); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2206,6 +2553,34 @@ ecode += 3; goto REPEATNOTCHAR; + case OP_NOTPOSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSUPTO: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 3; + goto REPEATNOTCHAR; + case OP_NOTSTAR: case OP_NOTMINSTAR: case OP_NOTPLUS: @@ -2245,7 +2620,7 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = 1; i <= min; i++) { GETCHARINC(d, eptr); @@ -2270,15 +2645,16 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(d, eptr); if (d < 256) d = md->lcc[d]; - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); + if (fc == d) RRETURN(MATCH_NOMATCH); + } } else @@ -2287,7 +2663,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM29); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); @@ -2306,7 +2682,7 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = min; i < max; i++) { int len = 1; @@ -2316,9 +2692,10 @@ if (fc == d) break; eptr += len; } - for(;;) + if (possessive) continue; + for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM30); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2333,9 +2710,10 @@ if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM31); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2354,7 +2732,7 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = 1; i <= min; i++) { GETCHARINC(d, eptr); @@ -2377,14 +2755,14 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(d, eptr); - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); + if (fc == d) RRETURN(MATCH_NOMATCH); } } else @@ -2393,7 +2771,7 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM33); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == *eptr++) RRETURN(MATCH_NOMATCH); @@ -2412,7 +2790,7 @@ /* UTF-8 mode */ if (utf8) { - register int d; + register unsigned int d; for (i = min; i < max; i++) { int len = 1; @@ -2421,9 +2799,10 @@ if (fc == d) break; eptr += len; } + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM34); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2438,9 +2817,10 @@ if (eptr >= md->end_subject || fc == *eptr) break; eptr++; } + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM35); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2469,17 +2849,45 @@ ecode += 3; goto REPEATTYPE; - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - c = *ecode++ - OP_TYPESTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; + case OP_TYPEPOSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSUPTO: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 3; + goto REPEATTYPE; + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + c = *ecode++ - OP_TYPESTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; /* Common code for all repeated single character type matches. Note that in UTF-8 mode, '.' matches a character of any length, but for the other @@ -2519,7 +2927,7 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); } break; @@ -2527,8 +2935,8 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + GETCHARINCTEST(c, eptr); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == ucp_Lu || prop_chartype == ucp_Ll || prop_chartype == ucp_Lt) == prop_fail_result) @@ -2540,8 +2948,8 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + GETCHARINCTEST(c, eptr); + prop_category = UCD_CATEGORY(c); if ((prop_category == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } @@ -2551,8 +2959,8 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + GETCHARINCTEST(c, eptr); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } @@ -2562,8 +2970,8 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + GETCHARINCTEST(c, eptr); + prop_script = UCD_SCRIPT(c); if ((prop_script == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } @@ -2571,7 +2979,6 @@ default: RRETURN(PCRE_ERROR_INTERNAL); - break; } } @@ -2583,7 +2990,7 @@ for (i = 1; i <= min; i++) { GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); while (eptr < md->end_subject) { @@ -2592,7 +2999,7 @@ { GETCHARLEN(c, eptr, len); } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category != ucp_M) break; eptr += len; } @@ -2610,20 +3017,156 @@ case OP_ANY: for (i = 1; i <= min; i++) { - if (eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && - IS_NEWLINE(eptr))) + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); eptr++; while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; } break; + case OP_ALLANY: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + break; + case OP_ANYBYTE: eptr += min; break; + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + + case 0x000a: + break; + + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) { @@ -2648,9 +3191,9 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0)) + (*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0)) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); } break; @@ -2668,9 +3211,9 @@ for (i = 1; i <= min; i++) { if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0)) + (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); } break; @@ -2692,27 +3235,116 @@ #endif /* SUPPORT_UTF8 */ /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. */ + than OP_PROP and OP_NOTPROP. We can assume that there are the minimum + number of bytes present, as this was tested above. */ switch(ctype) { case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) + for (i = 1; i <= min; i++) { - for (i = 1; i <= min; i++) - { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - eptr++; - } + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); + eptr++; } - else eptr += min; + break; + + case OP_ALLANY: + eptr += min; break; case OP_ANYBYTE: eptr += min; break; + /* Because of the CRLF case, we can't assume the minimum number of + bytes are present in this case. */ + + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + break; + + case 0x000b: + case 0x000c: + case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); @@ -2768,71 +3400,70 @@ case PT_ANY: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM36); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); if (prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_LAMP: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM37); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == ucp_Lu || prop_chartype == ucp_Ll || prop_chartype == ucp_Lt) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_GC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM38); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if ((prop_category == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_PC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM39); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ case PT_SC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM40); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_script = UCD_SCRIPT(c); if ((prop_script == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); } - break; + /* Control never gets here */ default: RRETURN(PCRE_ERROR_INTERNAL); - break; } } @@ -2843,11 +3474,11 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM41); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); while (eptr < md->end_subject) { @@ -2856,7 +3487,7 @@ { GETCHARLEN(c, eptr, len); } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category != ucp_M) break; eptr += len; } @@ -2872,20 +3503,122 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || - (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + (ctype == OP_ANY && IS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); switch(ctype) { - case OP_ANY: /* This is the DOTALL case */ + case OP_ANY: /* This is the non-NL case */ + case OP_ALLANY: + case OP_ANYBYTE: break; - case OP_ANYBYTE: + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + case 0x000a: + break; + + case 0x000b: + case 0x000c: + case 0x0085: + case 0x2028: + case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } break; case OP_NOT_DIGIT: @@ -2929,20 +3662,85 @@ { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + (ctype == OP_ANY && IS_NEWLINE(eptr))) RRETURN(MATCH_NOMATCH); c = *eptr++; switch(ctype) { - case OP_ANY: /* This is the DOTALL case */ + case OP_ANY: /* This is the non-NL case */ + case OP_ALLANY: + case OP_ANYBYTE: break; - case OP_ANYBYTE: + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x000d: + if (eptr < md->end_subject && *eptr == 0x0a) eptr++; + break; + + case 0x000a: + break; + + case 0x000b: + case 0x000c: + case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } break; case OP_NOT_DIGIT: @@ -2977,7 +3775,7 @@ /* Control never gets here */ } - /* If maximizing it is worth using inline code for speed, doing the type + /* If maximizing, it is worth using inline code for speed, doing the type test once at the start (i.e. keep it out of the loop). Again, keep the UTF-8 and UCP stuff separate. */ @@ -3007,7 +3805,7 @@ int len = 1; if (eptr >= md->end_subject) break; GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == ucp_Lu || prop_chartype == ucp_Ll || prop_chartype == ucp_Lt) == prop_fail_result) @@ -3022,7 +3820,7 @@ int len = 1; if (eptr >= md->end_subject) break; GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if ((prop_category == prop_value) == prop_fail_result) break; eptr+= len; @@ -3035,7 +3833,7 @@ int len = 1; if (eptr >= md->end_subject) break; GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_chartype = UCD_CHARTYPE(c); if ((prop_chartype == prop_value) == prop_fail_result) break; eptr+= len; @@ -3048,7 +3846,7 @@ int len = 1; if (eptr >= md->end_subject) break; GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_script = UCD_SCRIPT(c); if ((prop_script == prop_value) == prop_fail_result) break; eptr+= len; @@ -3058,12 +3856,13 @@ /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); + if (utf8) BACKCHAR(eptr); } } @@ -3076,7 +3875,7 @@ { if (eptr >= md->end_subject) break; GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category == ucp_M) break; while (eptr < md->end_subject) { @@ -3085,7 +3884,7 @@ { GETCHARLEN(c, eptr, len); } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category != ucp_M) break; eptr += len; } @@ -3093,20 +3892,21 @@ /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM45); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ for (;;) /* Move back over one extended */ { int len = 1; - BACKCHAR(eptr); if (!utf8) c = *eptr; else { + BACKCHAR(eptr); GETCHARLEN(c, eptr, len); } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + prop_category = UCD_CATEGORY(c); if (prop_category != ucp_M) break; eptr--; } @@ -3124,32 +3924,13 @@ switch(ctype) { case OP_ANY: - - /* Special code is required for UTF8, but when the maximum is - unlimited we don't need it, so we repeat the non-UTF8 code. This is - probably worth it, because .* is quite a common idiom. */ - if (max < INT_MAX) { - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - else + for (i = min; i < max; i++) { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; } } @@ -3157,34 +3938,124 @@ else { - if ((ims & PCRE_DOTALL) == 0) + for (i = min; i < max; i++) { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; - eptr++; - } - break; + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; } - else + } + break; + + case OP_ALLANY: + if (max < INT_MAX) + { + for (i = min; i < max; i++) { - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; + if (eptr >= md->end_subject) break; + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; } } + else eptr = md->end_subject; /* Unlimited UTF-8 repeat */ break; /* The byte case is the same as non-UTF8 */ case OP_ANYBYTE: c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; + if (c > (unsigned int)(md->end_subject - eptr)) + c = md->end_subject - eptr; eptr += c; break; + case OP_ANYNL: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c == 0x000d) + { + if (++eptr >= md->end_subject) break; + if (*eptr == 0x000a) eptr++; + } + else + { + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && + c != 0x0085 && c != 0x2028 && c != 0x2029))) + break; + eptr += len; + } + } + break; + + case OP_NOT_HSPACE: + case OP_HSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_HSPACE)) break; + eptr += len; + } + break; + + case OP_NOT_VSPACE: + case OP_VSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_VSPACE)) break; + eptr += len; + } + break; + case OP_NOT_DIGIT: for (i = min; i < max; i++) { @@ -3257,39 +4128,99 @@ /* eptr is now past the end of the maximum run */ + if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM46); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); } } else -#endif +#endif /* SUPPORT_UTF8 */ /* Not UTF-8 mode */ { switch(ctype) { case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) + for (i = min; i < max; i++) { - for (i = min; i < max; i++) + if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; + eptr++; + } + break; + + case OP_ALLANY: + case OP_ANYBYTE: + c = max - min; + if (c > (unsigned int)(md->end_subject - eptr)) + c = md->end_subject - eptr; + eptr += c; + break; + + case OP_ANYNL: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x000d) + { + if (++eptr >= md->end_subject) break; + if (*eptr == 0x000a) eptr++; + } + else { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && c != 0x0085))) break; eptr++; } - break; } - /* For DOTALL case, fall through and treat as \C */ + break; - case OP_ANYBYTE: - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; + case OP_NOT_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x09 || c == 0x20 || c == 0xa0) break; + eptr++; + } + break; + + case OP_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x09 && c != 0x20 && c != 0xa0) break; + eptr++; + } + break; + + case OP_NOT_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85) + break; + eptr++; + } + break; + + case OP_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85) + break; + eptr++; + } break; case OP_NOT_DIGIT: @@ -3352,9 +4283,10 @@ /* eptr is now past the end of the maximum run */ + if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM47); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -3366,14 +4298,12 @@ } /* Control never gets here */ - /* There's been some horrible disaster. Since all codes > OP_BRA are - for capturing brackets, and there shouldn't be any gaps between 0 and - OP_BRA, arrival here can only mean there is something seriously wrong - in the code above or the OP_xxx definitions. */ + /* There's been some horrible disaster. Arrival here can only mean there is + something seriously wrong in the code above or the OP_xxx definitions. */ default: DPRINTF(("Unknown opcode %d\n", *ecode)); - RRETURN(PCRE_ERROR_UNKNOWN_NODE); + RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); } /* Do not stick any code in here without much thought; it is assumed @@ -3382,6 +4312,35 @@ } /* End of main loop */ /* Control never reaches here */ + + +/* When compiling to use the heap rather than the stack for recursive calls to +match(), the RRETURN() macro jumps here. The number that is saved in +frame->Xwhere indicates which label we actually want to return to. */ + +#ifdef NO_RECURSE +#define LBL(val) case val: goto L_RM##val; +HEAP_RETURN: +switch (frame->Xwhere) + { + LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) + LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) + LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) + LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) + LBL(53) LBL(54) +#ifdef SUPPORT_UTF8 + LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30) + LBL(32) LBL(34) LBL(42) LBL(46) +#ifdef SUPPORT_UCP + LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) +#endif /* SUPPORT_UCP */ +#endif /* SUPPORT_UTF8 */ + default: + DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); + return PCRE_ERROR_INTERNAL; + } +#undef LBL +#endif /* NO_RECURSE */ } @@ -3394,6 +4353,7 @@ #ifdef NO_RECURSE #undef eptr #undef ecode +#undef mstart #undef offset_top #undef ims #undef eptrb @@ -3411,7 +4371,6 @@ #undef cur_is_word #undef condition -#undef minimize #undef prev_is_word #undef original_ims @@ -3467,7 +4426,7 @@ < -1 => some kind of unexpected problem */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, int offsetcount) @@ -3484,6 +4443,7 @@ BOOL firstline; BOOL first_byte_caseless = FALSE; BOOL req_byte_caseless = FALSE; +BOOL utf8; match_data match_block; match_data *md = &match_block; const uschar *tables; @@ -3553,7 +4513,7 @@ /* Set up other data */ anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->options & PCRE_STARTLINE) != 0; +startline = (re->flags & PCRE_STARTLINE) != 0; firstline = (re->options & PCRE_FIRSTLINE) != 0; /* The code starts after the real_pcre block and the capture name table. */ @@ -3567,7 +4527,8 @@ end_subject = md->end_subject; md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -md->utf8 = (re->options & PCRE_UTF8) != 0; +utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; +md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; md->notbol = (options & PCRE_NOTBOL) != 0; md->noteol = (options & PCRE_NOTEOL) != 0; @@ -3580,48 +4541,89 @@ md->lcc = tables + lcc_offset; md->ctypes = tables + ctypes_offset; -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ +/* Handle different \R options. */ -switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & - PCRE_NEWLINE_CRLF) +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) { - default: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; + case 0: + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; + else +#ifdef BSR_ANYCRLF + md->bsr_anycrlf = TRUE; +#else + md->bsr_anycrlf = FALSE; +#endif + break; + + case PCRE_BSR_ANYCRLF: + md->bsr_anycrlf = TRUE; + break; + + case PCRE_BSR_UNICODE: + md->bsr_anycrlf = FALSE; + break; + + default: return PCRE_ERROR_BADNEWLINE; + } + +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ + +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : + (pcre_uint32)options) & PCRE_NEWLINE_BITS) + { + case 0: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; } -if (newline > 255) +if (newline == -2) { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; } else { - md->nllen = 1; - md->nl[0] = newline; + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } } /* Partial matching is supported only for a restricted set of regexes at the moment. */ -if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) +if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) return PCRE_ERROR_BADPARTIAL; /* Check a UTF-8 string if required. Unfortunately there's no way of passing back the character offset. */ #ifdef SUPPORT_UTF8 -if (md->utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) +if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) { - if (_pcre_valid_utf8((uschar *)subject, length) >= 0) + if (_pcre_valid_utf8((USPTR)subject, length) >= 0) return PCRE_ERROR_BADUTF8; if (start_offset > 0 && start_offset < length) { - int tb = ((uschar *)subject)[start_offset]; + int tb = ((USPTR)subject)[start_offset]; if (tb > 127) { tb &= 0xc0; @@ -3685,7 +4687,7 @@ if (!anchored) { - if ((re->options & PCRE_FIRSTSET) != 0) + if ((re->flags & PCRE_FIRSTSET) != 0) { first_byte = re->first_byte & 255; if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) @@ -3700,19 +4702,23 @@ /* For anchored or unanchored matches, there may be a "last known required character" set. */ -if ((re->options & PCRE_REQCHSET) != 0) +if ((re->flags & PCRE_REQCHSET) != 0) { req_byte = re->req_byte & 255; req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ } + +/* ==========================================================================*/ + /* Loop for handling unanchored repeated matching attempts; for anchored regexs the loop runs just once. */ -do +for(;;) { USPTR save_end_subject = end_subject; + USPTR new_start_match; /* Reset the maximum number of extractions we might see. */ @@ -3723,55 +4729,94 @@ while (iptr < iend) *iptr++ = -1; } - /* Advance to a unique first char if possible. If firstline is TRUE, the - start of the match is constrained to the first line of a multiline string. - Implement this by temporarily adjusting end_subject so that we stop scanning - at a newline. If the match fails at the newline, later code breaks this loop. - */ + /* If firstline is TRUE, the start of the match is constrained to the first + line of a multiline string. That is, the match must be before or at the first + newline. Implement this by temporarily adjusting end_subject so that we stop + scanning at a newline. If the match fails at the newline, later code breaks + this loop. */ if (firstline) { USPTR t = start_match; - while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; +#ifdef SUPPORT_UTF8 + if (utf8) + { + while (t < md->end_subject && !IS_NEWLINE(t)) + { + t++; + while (t < end_subject && (*t & 0xc0) == 0x80) t++; + } + } + else +#endif + while (t < md->end_subject && !IS_NEWLINE(t)) t++; end_subject = t; } - /* Now test for a unique first byte */ + /* There are some optimizations that avoid running the match if a known + starting point is not found, or if a known later character is not present. + However, there is an option that disables these, for testing and for ensuring + that all callouts do actually occur. */ - if (first_byte >= 0) + if ((options & PCRE_NO_START_OPTIMIZE) == 0) { - if (first_byte_caseless) - while (start_match < end_subject && - md->lcc[*start_match] != first_byte) - start_match++; - else - while (start_match < end_subject && *start_match != first_byte) - start_match++; - } + /* Advance to a unique first byte if there is one. */ - /* Or to just after a linebreak for a multiline match if possible */ + if (first_byte >= 0) + { + if (first_byte_caseless) + while (start_match < end_subject && md->lcc[*start_match] != first_byte) + start_match++; + else + while (start_match < end_subject && *start_match != first_byte) + start_match++; + } - else if (startline) - { - if (start_match >= md->start_subject + md->nllen + - start_offset) + /* Or to just after a linebreak for a multiline match */ + + else if (startline) { - while (start_match <= end_subject && - !IS_NEWLINE(start_match - md->nllen)) - start_match++; + if (start_match > md->start_subject + start_offset) + { +#ifdef SUPPORT_UTF8 + if (utf8) + { + while (start_match < end_subject && !WAS_NEWLINE(start_match)) + { + start_match++; + while(start_match < end_subject && (*start_match & 0xc0) == 0x80) + start_match++; + } + } + else +#endif + while (start_match < end_subject && !WAS_NEWLINE(start_match)) + start_match++; + + /* If we have just passed a CR and the newline option is ANY or ANYCRLF, + and we are now at a LF, advance the match position by one more character. + */ + + if (start_match[-1] == CHAR_CR && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + start_match < end_subject && + *start_match == CHAR_NL) + start_match++; + } } - } - /* Or to a non-unique first char after study */ + /* Or to a non-unique first byte after study */ - else if (start_bits != NULL) - { - while (start_match < end_subject) + else if (start_bits != NULL) { - register unsigned int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; + while (start_match < end_subject) + { + register unsigned int c = *start_match; + if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; + else break; + } } - } + } /* Starting optimizations */ /* Restore fudged end_subject */ @@ -3783,23 +4828,25 @@ printf("\n"); #endif - /* If req_byte is set, we know that that character must appear in the subject - for the match to succeed. If the first character is set, req_byte must be - later in the subject; otherwise the test starts at the match point. This - optimization can save a huge amount of backtracking in patterns with nested - unlimited repeats that aren't going to match. Writing separate code for - cased/caseless versions makes it go faster, as does using an autoincrement - and backing off on a match. - - HOWEVER: when the subject string is very, very long, searching to its end can - take a long time, and give bad performance on quite ordinary patterns. This - showed up when somebody was matching /^C/ on a 32-megabyte string... so we - don't do this when the string is sufficiently long. + /* If req_byte is set, we know that that character must appear in the + subject for the match to succeed. If the first character is set, req_byte + must be later in the subject; otherwise the test starts at the match point. + This optimization can save a huge amount of backtracking in patterns with + nested unlimited repeats that aren't going to match. Writing separate code + for cased/caseless versions makes it go faster, as does using an + autoincrement and backing off on a match. + + HOWEVER: when the subject string is very, very long, searching to its end + can take a long time, and give bad performance on quite ordinary patterns. + This showed up when somebody was matching something like /^\d+C/ on a + 32-megabyte string... so we don't do this when the string is sufficiently + long. - ALSO: this processing is disabled when partial matching is requested. - */ + ALSO: this processing is disabled when partial matching is requested, or if + disabling is explicitly requested. */ - if (req_byte >= 0 && + if ((options & PCRE_NO_START_OPTIMIZE) == 0 && + req_byte >= 0 && end_subject - start_match < REQ_BYTE_MAX && !md->partial) { @@ -3826,9 +4873,14 @@ } } - /* If we can't find the required character, break the matching loop */ + /* If we can't find the required character, break the matching loop, + forcing a match failure. */ - if (p >= end_subject) break; + if (p >= end_subject) + { + rc = MATCH_NOMATCH; + break; + } /* If we have found the required character, save the point where we found it, so that we don't search again next time round the loop if @@ -3838,49 +4890,105 @@ } } - /* When a match occurs, substrings will be set for all internal extractions; - we just need to set up the whole thing as substring 0 before returning. If - there were too many extractions, set the return code to zero. In the case - where we had to get some local store to hold offsets for backreferences, copy - those back references that we can. In this case there need not be overflow - if certain parts of the pattern were not used. */ + /* OK, we can now run the match. */ - md->start_match = start_match; + md->start_match_ptr = start_match; md->match_call_count = 0; + rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0); - rc = match(start_match, md->start_code, 2, md, ims, NULL, match_isgroup, 0); - - /* When the result is no match, if the subject's first character was a - newline and the PCRE_FIRSTLINE option is set, break (which will return - PCRE_ERROR_NOMATCH). The option requests that a match occur before the first - newline in the subject. Otherwise, advance the pointer to the next character - and continue - but the continuation will actually happen only when the - pattern is not anchored. */ - - if (rc == MATCH_NOMATCH) + switch(rc) { - if (firstline && - start_match <= md->end_subject - md->nllen && - IS_NEWLINE(start_match)) - break; - start_match++; + /* NOMATCH and PRUNE advance by one character. THEN at this level acts + exactly like PRUNE. */ + + case MATCH_NOMATCH: + case MATCH_PRUNE: + case MATCH_THEN: + new_start_match = start_match + 1; #ifdef SUPPORT_UTF8 - if (md->utf8) - while(start_match < end_subject && (*start_match & 0xc0) == 0x80) - start_match++; + if (utf8) + while(new_start_match < end_subject && (*new_start_match & 0xc0) == 0x80) + new_start_match++; #endif - continue; - } + break; - if (rc != MATCH_MATCH) - { - DPRINTF((">>>> error: returning %d\n", rc)); - return rc; + /* SKIP passes back the next starting point explicitly. */ + + case MATCH_SKIP: + new_start_match = md->start_match_ptr; + break; + + /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ + + case MATCH_COMMIT: + rc = MATCH_NOMATCH; + goto ENDLOOP; + + /* Any other return is some kind of error. */ + + default: + goto ENDLOOP; } - /* We have a match! Copy the offset information from temporary store if - necessary */ + /* Control reaches here for the various types of "no match at this point" + result. Reset the code to MATCH_NOMATCH for subsequent checking. */ + + rc = MATCH_NOMATCH; + + /* If PCRE_FIRSTLINE is set, the match must happen before or at the first + newline in the subject (though it may continue over the newline). Therefore, + if we have just failed to match, starting at a newline, do not continue. */ + + if (firstline && IS_NEWLINE(start_match)) break; + + /* Advance to new matching position */ + + start_match = new_start_match; + + /* Break the loop if the pattern is anchored or if we have passed the end of + the subject. */ + + if (anchored || start_match > end_subject) break; + + /* If we have just passed a CR and we are now at a LF, and the pattern does + not contain any explicit matches for \r or \n, and the newline option is CRLF + or ANY or ANYCRLF, advance the match position by one more character. */ + + if (start_match[-1] == CHAR_CR && + start_match < end_subject && + *start_match == CHAR_NL && + (re->flags & PCRE_HASCRORLF) == 0 && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2)) + start_match++; + + } /* End of for(;;) "bumpalong" loop */ + +/* ==========================================================================*/ + +/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping +conditions is true: +(1) The pattern is anchored or the match was failed by (*COMMIT); + +(2) We are past the end of the subject; + +(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because + this option requests that a match occur at or before the first newline in + the subject. + +When we have a match and the offset vector is big enough to deal with any +backreferences, captured substring offsets will already be set up. In the case +where we had to get some local store to hold offsets for backreference +processing, copy those that we can. In this case there need not be overflow if +certain parts of the pattern were not used, even though there are more +capturing parentheses than vector slots. */ + +ENDLOOP: + +if (rc == MATCH_MATCH) + { if (using_temporary_offsets) { if (offsetcount >= 4) @@ -3889,18 +4997,23 @@ (offsetcount - 2) * sizeof(int)); DPRINTF(("Copied offsets from temporary memory\n")); } - if (md->end_offset_top > offsetcount) - md->offset_overflow = TRUE; - + if (md->end_offset_top > offsetcount) md->offset_overflow = TRUE; DPRINTF(("Freeing temporary memory\n")); (pcre_free)(md->offset_vector); } + /* Set the return code to the number of captured strings, or 0 if there are + too many to fit into the vector. */ + rc = md->offset_overflow? 0 : md->end_offset_top/2; + /* If there is space, set up the whole thing as substring 0. The value of + md->start_match_ptr might be modified if \K was encountered on the success + matching path. */ + if (offsetcount < 2) rc = 0; else { - offsets[0] = start_match - md->start_subject; + offsets[0] = md->start_match_ptr - md->start_subject; offsets[1] = md->end_match_ptr - md->start_subject; } @@ -3908,9 +5021,8 @@ return rc; } -/* This "while" is the end of the "do" above */ - -while (!anchored && start_match <= end_subject); +/* Control gets here if there has been an error, or if the overall match +attempt has failed at all permitted starting positions. */ if (using_temporary_offsets) { @@ -3918,7 +5030,12 @@ (pcre_free)(md->offset_vector); } -if (md->partial && md->hitend) +if (rc != MATCH_NOMATCH) + { + DPRINTF((">>>> error: returning %d\n", rc)); + return rc; + } +else if (md->partial && md->hitend) { DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); return PCRE_ERROR_PARTIAL; Modified: freeswitch/trunk/libs/pcre/pcre_fullinfo.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_fullinfo.c (original) +++ freeswitch/trunk/libs/pcre/pcre_fullinfo.c Mon Jun 8 18:51:30 2009 @@ -2,11 +2,11 @@ * Perl-Compatible Regular Expressions * *************************************************/ -/*PCRE is a library of functions to support regular expressions whose syntax +/* PCRE is a library of functions to support regular expressions whose syntax and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,6 +42,10 @@ information about a compiled pattern. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -61,7 +65,7 @@ Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, void *where) { @@ -85,7 +89,7 @@ switch (what) { case PCRE_INFO_OPTIONS: - *((unsigned long int *)where) = re->options & PUBLIC_OPTIONS; + *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS; break; case PCRE_INFO_SIZE: @@ -106,8 +110,8 @@ case PCRE_INFO_FIRSTBYTE: *((int *)where) = - ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; + ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; break; /* Make sure we pass back the pointer to the bit vector in the external @@ -121,7 +125,7 @@ case PCRE_INFO_LASTLITERAL: *((int *)where) = - ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1; + ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1; break; case PCRE_INFO_NAMEENTRYSIZE: @@ -140,6 +144,18 @@ *((const uschar **)where) = (const uschar *)(_pcre_default_tables); break; + case PCRE_INFO_OKPARTIAL: + *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; + break; + + case PCRE_INFO_JCHANGED: + *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; + break; + + case PCRE_INFO_HASCRORLF: + *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; + break; + default: return PCRE_ERROR_BADOPTION; } Modified: freeswitch/trunk/libs/pcre/pcre_get.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_get.c (original) +++ freeswitch/trunk/libs/pcre/pcre_get.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -43,6 +43,10 @@ for these functions came from Scott Wimer. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -61,7 +65,7 @@ (PCRE_ERROR_NOSUBSTRING) if not found */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_get_stringnumber(const pcre *code, const char *stringname) { int rc; @@ -110,7 +114,7 @@ (PCRE_ERROR_NOSUBSTRING) if not found */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_get_stringtable_entries(const pcre *code, const char *stringname, char **firstptr, char **lastptr) { @@ -185,7 +189,7 @@ int entrysize; char *first, *last; uschar *entry; -if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0) +if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) return pcre_get_stringnumber(code, stringname); entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); if (entrysize <= 0) return entrysize; @@ -227,7 +231,7 @@ PCRE_ERROR_NOSUBSTRING (-7) no such captured substring */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_copy_substring(const char *subject, int *ovector, int stringcount, int stringnumber, char *buffer, int size) { @@ -272,7 +276,7 @@ PCRE_ERROR_NOSUBSTRING (-7) no such captured substring */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector, int stringcount, const char *stringname, char *buffer, int size) { @@ -304,7 +308,7 @@ PCRE_ERROR_NOMEMORY (-6) failed to get store */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr) { @@ -349,7 +353,7 @@ Returns: nothing */ -void +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION pcre_free_substring_list(const char **pointer) { (pcre_free)((void *)pointer); @@ -382,7 +386,7 @@ PCRE_ERROR_NOSUBSTRING (-7) substring not present */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_get_substring(const char *subject, int *ovector, int stringcount, int stringnumber, const char **stringptr) { @@ -429,14 +433,13 @@ PCRE_ERROR_NOSUBSTRING (-7) no such captured substring */ -int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, int stringcount, const char *stringname, const char **stringptr) { int n = get_first_set(code, stringname, ovector); if (n <= 0) return n; return pcre_get_substring(subject, ovector, stringcount, n, stringptr); - } @@ -453,7 +456,7 @@ Returns: nothing */ -void +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION pcre_free_substring(const char *pointer) { (pcre_free)((void *)pointer); Modified: freeswitch/trunk/libs/pcre/pcre_globals.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_globals.c (original) +++ freeswitch/trunk/libs/pcre/pcre_globals.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -46,24 +46,18 @@ all threads. However, when compiling for Virtual Pascal, things are done differently, and global variables are not used (see pcre.in). */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif #include "pcre_internal.h" - #ifndef VPCOMPAT -#ifdef __cplusplus -extern "C" void *(*pcre_malloc)(size_t) = malloc; -extern "C" void (*pcre_free)(void *) = free; -extern "C" void *(*pcre_stack_malloc)(size_t) = malloc; -extern "C" void (*pcre_stack_free)(void *) = free; -extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL; -#else -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; -void *(*pcre_stack_malloc)(size_t) = malloc; -void (*pcre_stack_free)(void *) = free; -int (*pcre_callout)(pcre_callout_block *) = NULL; -#endif +PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free; +PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free; +PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL; #endif /* End of pcre_globals.c */ Modified: freeswitch/trunk/libs/pcre/pcre_info.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_info.c (original) +++ freeswitch/trunk/libs/pcre/pcre_info.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -43,6 +43,10 @@ deprecated, as it has been superseded by pcre_fullinfo(). */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -68,7 +72,7 @@ or negative values on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_info(const pcre *argument_re, int *optptr, int *first_byte) { real_pcre internal_re; @@ -79,10 +83,10 @@ re = _pcre_try_flipped(re, &internal_re, NULL, NULL); if (re == NULL) return PCRE_ERROR_BADMAGIC; } -if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS); +if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_COMPILE_OPTIONS); if (first_byte != NULL) - *first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; + *first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; return re->top_bracket; } Modified: freeswitch/trunk/libs/pcre/pcre_internal.h ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_internal.h (original) +++ freeswitch/trunk/libs/pcre/pcre_internal.h Mon Jun 8 18:51:30 2009 @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -51,22 +51,36 @@ #define PCRE_DEBUG #endif +/* We do not support both EBCDIC and UTF-8 at the same time. The "configure" +script prevents both being selected, but not everybody uses "configure". */ + +#if defined EBCDIC && defined SUPPORT_UTF8 +#error The use of both EBCDIC and SUPPORT_UTF8 is not supported. +#endif + +/* If SUPPORT_UCP is defined, SUPPORT_UTF8 must also be defined. The +"configure" script ensures this, but not everybody uses "configure". */ + +#if defined SUPPORT_UCP && !defined SUPPORT_UTF8 +#define SUPPORT_UTF8 1 +#endif + /* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef inline, and there are *still* stupid compilers about that don't like indented pre-processor statements, or at least there were when I first wrote this. After -all, it had only been about 10 years then... */ +all, it had only been about 10 years then... + +It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so +be absolutely sure we get our version. */ +#undef DPRINTF #ifdef PCRE_DEBUG #define DPRINTF(p) printf p #else -#define DPRINTF(p) /*nothing*/ +#define DPRINTF(p) /* Nothing */ #endif -/* Get the definitions provided by running "configure" */ - -#include "config.h" - /* Standard C headers plus the external interface definition. The only time setjmp and stdarg are used is when NO_RECURSE is set. */ @@ -79,8 +93,71 @@ #include <stdlib.h> #include <string.h> -#ifndef PCRE_SPY -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ +/* When compiling a DLL for Windows, the exported symbols have to be declared +using some MS magic. I found some useful information on this web page: +http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the +information there, using __declspec(dllexport) without "extern" we have a +definition; with "extern" we have a declaration. The settings here override the +setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, +which is all that is needed for applications (they just import the symbols). We +use: + + PCRE_EXP_DECL for declarations + PCRE_EXP_DEFN for definitions of exported functions + PCRE_EXP_DATA_DEFN for definitions of exported variables + +The reason for the two DEFN macros is that in non-Windows environments, one +does not want to have "extern" before variable definitions because it leads to +compiler warnings. So we distinguish between functions and variables. In +Windows, the two should always be the same. + +The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, +which is an application, but needs to import this file in order to "peek" at +internals, can #include pcre.h first to get an application's-eye view. + +In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, +special-purpose environments) might want to stick other stuff in front of +exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and +PCRE_EXP_DATA_DEFN only if they are not already set. */ + +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 +# ifndef PCRE_STATIC +# define PCRE_EXP_DECL extern __declspec(dllexport) +# define PCRE_EXP_DEFN __declspec(dllexport) +# define PCRE_EXP_DATA_DEFN __declspec(dllexport) +# else +# define PCRE_EXP_DECL extern +# define PCRE_EXP_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# else +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +# ifndef PCRE_EXP_DEFN +# define PCRE_EXP_DEFN PCRE_EXP_DECL +# endif +# ifndef PCRE_EXP_DATA_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# endif +#endif + +/* When compiling with the MSVC compiler, it is sometimes necessary to include +a "calling convention" before exported function names. (This is secondhand +information; I know nothing about MSVC myself). For example, something like + + void __cdecl function(....) + +might be needed. In order so make this easy, all the exported functions have +PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not +set, we ensure here that it has no effect. */ + +#ifndef PCRE_CALL_CONVENTION +#define PCRE_CALL_CONVENTION #endif /* We need to have types that specify unsigned 16-bit and 32-bit integers. We @@ -91,16 +168,20 @@ #if USHRT_MAX == 65535 typedef unsigned short pcre_uint16; + typedef short pcre_int16; #elif UINT_MAX == 65535 typedef unsigned int pcre_uint16; + typedef int pcre_int16; #else #error Cannot determine a type for 16-bit unsigned integers #endif #if UINT_MAX == 4294967295 typedef unsigned int pcre_uint32; + typedef int pcre_int32; #elif ULONG_MAX == 4294967295 typedef unsigned long int pcre_uint32; + typedef long int pcre_int32; #else #error Cannot determine a type for 32-bit unsigned integers #endif @@ -114,13 +195,49 @@ typedef unsigned char uschar; -/* PCRE is able to support 3 different kinds of newline (CR, LF, CRLF). The -following macro is used to package up testing for newlines. NLBLOCK is defined -in the various modules to indicate in which datablock the parameters exist. */ +/* This is an unsigned int value that no character can ever have. UTF-8 +characters only go up to 0x7fffffff (though Unicode doesn't go beyond +0x0010ffff). */ + +#define NOTACHAR 0xffffffff + +/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, +"any" and "anycrlf" at present). The following macros are used to package up +testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various +modules to indicate in which datablock the parameters exist, and what the +start/end of string field names are. */ + +#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ +#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ + +/* This macro checks for a newline at the given position */ #define IS_NEWLINE(p) \ - ((p)[0] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1])) + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) < NLBLOCK->PSEND && \ + _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ + utf8)) \ + : \ + ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ + (p)[0] == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \ + ) \ + ) + +/* This macro checks for a newline immediately preceding the given position */ + +#define WAS_NEWLINE(p) \ + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) > NLBLOCK->PSSTART && \ + _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ + &(NLBLOCK->nllen), utf8)) \ + : \ + ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ + (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \ + ) \ + ) /* When PCRE is compiled as a C++ library, the subject pointer can be replaced with a custom type. This makes it possible, for example, to allow pcre_exec() @@ -139,6 +256,8 @@ #define USPTR const unsigned char * #endif + + /* Include the public PCRE header and the definitions of UCP character property values. */ @@ -150,7 +269,9 @@ option on the command line. */ #ifdef VPCOMPAT +#define strlen(s) _strlen(s) #define strncmp(s1,s2,m) _strncmp(s1,s2,m) +#define memcmp(s,c,n) _memcmp(s,c,n) #define memcpy(d,s,n) _memcpy(d,s,n) #define memmove(d,s,n) _memmove(d,s,n) #define memset(s,c,n) _memset(s,c,n) @@ -159,23 +280,31 @@ /* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). This assumes -that all calls to memmove are moving strings upwards in store, which is the -case in PCRE. */ +neither (there some non-Unix environments where this is the case). */ -#if ! HAVE_MEMMOVE +#ifndef HAVE_MEMMOVE #undef memmove /* some systems may have a macro */ -#if HAVE_BCOPY +#ifdef HAVE_BCOPY #define memmove(a, b, c) bcopy(b, a, c) #else /* HAVE_BCOPY */ static void * -pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) +pcre_memmove(void *d, const void *s, size_t n) { size_t i; -dest += n; -src += n; -for (i = 0; i < n; ++i) *(--dest) = *(--src); -return dest; +unsigned char *dest = (unsigned char *)d; +const unsigned char *src = (const unsigned char *)s; +if (dest > src) + { + dest += n; + src += n; + for (i = 0; i < n; ++i) *(--dest) = *(--src); + return (void *)dest; + } +else + { + for (i = 0; i < n; ++i) *dest++ = *src++; + return (void *)(dest - n); + } } #define memmove(a, b, c) pcre_memmove(a, b, c) #endif /* not HAVE_BCOPY */ @@ -261,7 +390,9 @@ /* When UTF-8 encoding is being used, a character is no longer just a single byte. The macros for character handling generate simple sequences when used in -byte-mode, and more complicated ones for UTF-8 characters. */ +byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should +never be called in byte mode. To make sure it can never even appear when UTF-8 +support is omitted, we don't even define it. */ #ifndef SUPPORT_UTF8 #define GETCHAR(c, eptr) c = *eptr; @@ -269,7 +400,7 @@ #define GETCHARINC(c, eptr) c = *eptr++; #define GETCHARINCTEST(c, eptr) c = *eptr++; #define GETCHARLEN(c, eptr, len) c = *eptr; -#define BACKCHAR(eptr) +/* #define BACKCHAR(eptr) */ #else /* SUPPORT_UTF8 */ @@ -278,7 +409,7 @@ #define GETCHAR(c, eptr) \ c = *eptr; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -296,7 +427,7 @@ #define GETCHARTEST(c, eptr) \ c = *eptr; \ - if (utf8 && (c & 0xc0) == 0xc0) \ + if (utf8 && c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -314,7 +445,7 @@ #define GETCHARINC(c, eptr) \ c = *eptr++; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ { \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ int gcss = 6*gcaa; \ @@ -330,7 +461,7 @@ #define GETCHARINCTEST(c, eptr) \ c = *eptr++; \ - if (utf8 && (c & 0xc0) == 0xc0) \ + if (utf8 && c >= 0xc0) \ { \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ int gcss = 6*gcaa; \ @@ -347,7 +478,27 @@ #define GETCHARLEN(c, eptr, len) \ c = *eptr; \ - if ((c & 0xc0) == 0xc0) \ + if (c >= 0xc0) \ + { \ + int gcii; \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + for (gcii = 1; gcii <= gcaa; gcii++) \ + { \ + gcss -= 6; \ + c |= (eptr[gcii] & 0x3f) << gcss; \ + } \ + len += gcaa; \ + } + +/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the +pointer, incrementing length if there are extra bytes. This is called when we +know we are in UTF-8 mode. */ + +#define GETCHARLENTEST(c, eptr, len) \ + c = *eptr; \ + if (utf8 && c >= 0xc0) \ { \ int gcii; \ int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ @@ -362,9 +513,10 @@ } /* If the pointer is not at the start of a character, move it back until -it is. Called only in UTF-8 mode. */ +it is. This is called only in UTF-8 mode - we don't put a test within the macro +because almost all calls are already within a block of UTF-8 only code. */ -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--; +#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- #endif @@ -381,17 +533,16 @@ #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) -/* Private options flags start at the most significant end of the four bytes. -The public options defined in pcre.h start at the least significant end. Make -sure they don't overlap! The bits are getting a bit scarce now -- when we run -out, there is a dummy word in the structure that could be used for the private -bits. */ - -#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ -#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */ +/* Private flags containing information about the compiled regex. They used to +live at the top end of the options word, but that got almost full, so now they +are in a 16-bit flags word. */ + +#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ +#define PCRE_FIRSTSET 0x0002 /* first_byte is set */ +#define PCRE_REQCHSET 0x0004 /* req_byte is set */ +#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */ +#define PCRE_JCHANGED 0x0010 /* j option used in regex */ +#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */ /* Options for the "extra" block produced by pcre_study(). */ @@ -400,20 +551,25 @@ /* Masks for identifying the public options that are permitted at compile time, run time, or study time, respectively. */ -#define PUBLIC_OPTIONS \ +#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ + PCRE_NEWLINE_ANYCRLF) + +#define PUBLIC_COMPILE_OPTIONS \ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ + PCRE_JAVASCRIPT_COMPAT) #define PUBLIC_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ + PCRE_NO_START_OPTIMIZE) #define PUBLIC_DFA_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_CR| \ - PCRE_NEWLINE_LF) + PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \ + PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE) #define PUBLIC_STUDY_OPTIONS 0 /* None defined */ @@ -438,38 +594,572 @@ #define REQ_CASELESS 0x0100 /* indicates caselessness */ #define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ -/* Miscellaneous definitions */ +/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in +environments where these macros are defined elsewhere. Unfortunately, there +is no way to do the same for the typedef. */ typedef int BOOL; +#ifndef FALSE #define FALSE 0 #define TRUE 1 +#endif + +/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal +character constants like '*' because the compiler would emit their EBCDIC code, +which is different from their ASCII/UTF-8 code. Instead we define macros for +the characters so that they always use the ASCII/UTF-8 code when UTF-8 support +is enabled. When UTF-8 support is not enabled, the definitions use character +literals. Both character and string versions of each character are needed, and +there are some longer strings as well. + +This means that, on EBCDIC platforms, the PCRE library can handle either +EBCDIC, or UTF-8, but not both. To support both in the same compiled library +would need different lookups depending on whether PCRE_UTF8 was set or not. +This would make it impossible to use characters in switch/case statements, +which would reduce performance. For a theoretical use (which nobody has asked +for) in a minority area (EBCDIC platforms), this is not sensible. Any +application that did need both could compile two versions of the library, using +macros to give the functions distinct names. */ + +#ifndef SUPPORT_UTF8 -/* Escape items that are just an encoding of a particular data value. Note that -ESC_n is defined as yet another macro, which is set in config.h to either \n -(the default) or \r (which some people want). */ +/* UTF-8 support is not enabled; use the platform-dependent character literals +so that PCRE works on both ASCII and EBCDIC platforms, in non-UTF-mode only. */ + +#define CHAR_HT '\t' +#define CHAR_VT '\v' +#define CHAR_FF '\f' +#define CHAR_CR '\r' +#define CHAR_NL '\n' +#define CHAR_BS '\b' +#define CHAR_BEL '\a' +#ifdef EBCDIC +#define CHAR_ESC '\047' +#define CHAR_DEL '\007' +#else +#define CHAR_ESC '\033' +#define CHAR_DEL '\177' +#endif + +#define CHAR_SPACE ' ' +#define CHAR_EXCLAMATION_MARK '!' +#define CHAR_QUOTATION_MARK '"' +#define CHAR_NUMBER_SIGN '#' +#define CHAR_DOLLAR_SIGN '$' +#define CHAR_PERCENT_SIGN '%' +#define CHAR_AMPERSAND '&' +#define CHAR_APOSTROPHE '\'' +#define CHAR_LEFT_PARENTHESIS '(' +#define CHAR_RIGHT_PARENTHESIS ')' +#define CHAR_ASTERISK '*' +#define CHAR_PLUS '+' +#define CHAR_COMMA ',' +#define CHAR_MINUS '-' +#define CHAR_DOT '.' +#define CHAR_SLASH '/' +#define CHAR_0 '0' +#define CHAR_1 '1' +#define CHAR_2 '2' +#define CHAR_3 '3' +#define CHAR_4 '4' +#define CHAR_5 '5' +#define CHAR_6 '6' +#define CHAR_7 '7' +#define CHAR_8 '8' +#define CHAR_9 '9' +#define CHAR_COLON ':' +#define CHAR_SEMICOLON ';' +#define CHAR_LESS_THAN_SIGN '<' +#define CHAR_EQUALS_SIGN '=' +#define CHAR_GREATER_THAN_SIGN '>' +#define CHAR_QUESTION_MARK '?' +#define CHAR_COMMERCIAL_AT '@' +#define CHAR_A 'A' +#define CHAR_B 'B' +#define CHAR_C 'C' +#define CHAR_D 'D' +#define CHAR_E 'E' +#define CHAR_F 'F' +#define CHAR_G 'G' +#define CHAR_H 'H' +#define CHAR_I 'I' +#define CHAR_J 'J' +#define CHAR_K 'K' +#define CHAR_L 'L' +#define CHAR_M 'M' +#define CHAR_N 'N' +#define CHAR_O 'O' +#define CHAR_P 'P' +#define CHAR_Q 'Q' +#define CHAR_R 'R' +#define CHAR_S 'S' +#define CHAR_T 'T' +#define CHAR_U 'U' +#define CHAR_V 'V' +#define CHAR_W 'W' +#define CHAR_X 'X' +#define CHAR_Y 'Y' +#define CHAR_Z 'Z' +#define CHAR_LEFT_SQUARE_BRACKET '[' +#define CHAR_BACKSLASH '\\' +#define CHAR_RIGHT_SQUARE_BRACKET ']' +#define CHAR_CIRCUMFLEX_ACCENT '^' +#define CHAR_UNDERSCORE '_' +#define CHAR_GRAVE_ACCENT '`' +#define CHAR_a 'a' +#define CHAR_b 'b' +#define CHAR_c 'c' +#define CHAR_d 'd' +#define CHAR_e 'e' +#define CHAR_f 'f' +#define CHAR_g 'g' +#define CHAR_h 'h' +#define CHAR_i 'i' +#define CHAR_j 'j' +#define CHAR_k 'k' +#define CHAR_l 'l' +#define CHAR_m 'm' +#define CHAR_n 'n' +#define CHAR_o 'o' +#define CHAR_p 'p' +#define CHAR_q 'q' +#define CHAR_r 'r' +#define CHAR_s 's' +#define CHAR_t 't' +#define CHAR_u 'u' +#define CHAR_v 'v' +#define CHAR_w 'w' +#define CHAR_x 'x' +#define CHAR_y 'y' +#define CHAR_z 'z' +#define CHAR_LEFT_CURLY_BRACKET '{' +#define CHAR_VERTICAL_LINE '|' +#define CHAR_RIGHT_CURLY_BRACKET '}' +#define CHAR_TILDE '~' + +#define STR_HT "\t" +#define STR_VT "\v" +#define STR_FF "\f" +#define STR_CR "\r" +#define STR_NL "\n" +#define STR_BS "\b" +#define STR_BEL "\a" +#ifdef EBCDIC +#define STR_ESC "\047" +#define STR_DEL "\007" +#else +#define STR_ESC "\033" +#define STR_DEL "\177" +#endif + +#define STR_SPACE " " +#define STR_EXCLAMATION_MARK "!" +#define STR_QUOTATION_MARK "\"" +#define STR_NUMBER_SIGN "#" +#define STR_DOLLAR_SIGN "$" +#define STR_PERCENT_SIGN "%" +#define STR_AMPERSAND "&" +#define STR_APOSTROPHE "'" +#define STR_LEFT_PARENTHESIS "(" +#define STR_RIGHT_PARENTHESIS ")" +#define STR_ASTERISK "*" +#define STR_PLUS "+" +#define STR_COMMA "," +#define STR_MINUS "-" +#define STR_DOT "." +#define STR_SLASH "/" +#define STR_0 "0" +#define STR_1 "1" +#define STR_2 "2" +#define STR_3 "3" +#define STR_4 "4" +#define STR_5 "5" +#define STR_6 "6" +#define STR_7 "7" +#define STR_8 "8" +#define STR_9 "9" +#define STR_COLON ":" +#define STR_SEMICOLON ";" +#define STR_LESS_THAN_SIGN "<" +#define STR_EQUALS_SIGN "=" +#define STR_GREATER_THAN_SIGN ">" +#define STR_QUESTION_MARK "?" +#define STR_COMMERCIAL_AT "@" +#define STR_A "A" +#define STR_B "B" +#define STR_C "C" +#define STR_D "D" +#define STR_E "E" +#define STR_F "F" +#define STR_G "G" +#define STR_H "H" +#define STR_I "I" +#define STR_J "J" +#define STR_K "K" +#define STR_L "L" +#define STR_M "M" +#define STR_N "N" +#define STR_O "O" +#define STR_P "P" +#define STR_Q "Q" +#define STR_R "R" +#define STR_S "S" +#define STR_T "T" +#define STR_U "U" +#define STR_V "V" +#define STR_W "W" +#define STR_X "X" +#define STR_Y "Y" +#define STR_Z "Z" +#define STR_LEFT_SQUARE_BRACKET "[" +#define STR_BACKSLASH "\\" +#define STR_RIGHT_SQUARE_BRACKET "]" +#define STR_CIRCUMFLEX_ACCENT "^" +#define STR_UNDERSCORE "_" +#define STR_GRAVE_ACCENT "`" +#define STR_a "a" +#define STR_b "b" +#define STR_c "c" +#define STR_d "d" +#define STR_e "e" +#define STR_f "f" +#define STR_g "g" +#define STR_h "h" +#define STR_i "i" +#define STR_j "j" +#define STR_k "k" +#define STR_l "l" +#define STR_m "m" +#define STR_n "n" +#define STR_o "o" +#define STR_p "p" +#define STR_q "q" +#define STR_r "r" +#define STR_s "s" +#define STR_t "t" +#define STR_u "u" +#define STR_v "v" +#define STR_w "w" +#define STR_x "x" +#define STR_y "y" +#define STR_z "z" +#define STR_LEFT_CURLY_BRACKET "{" +#define STR_VERTICAL_LINE "|" +#define STR_RIGHT_CURLY_BRACKET "}" +#define STR_TILDE "~" + +#define STRING_ACCEPT0 "ACCEPT\0" +#define STRING_COMMIT0 "COMMIT\0" +#define STRING_F0 "F\0" +#define STRING_FAIL0 "FAIL\0" +#define STRING_PRUNE0 "PRUNE\0" +#define STRING_SKIP0 "SKIP\0" +#define STRING_THEN "THEN" + +#define STRING_alpha0 "alpha\0" +#define STRING_lower0 "lower\0" +#define STRING_upper0 "upper\0" +#define STRING_alnum0 "alnum\0" +#define STRING_ascii0 "ascii\0" +#define STRING_blank0 "blank\0" +#define STRING_cntrl0 "cntrl\0" +#define STRING_digit0 "digit\0" +#define STRING_graph0 "graph\0" +#define STRING_print0 "print\0" +#define STRING_punct0 "punct\0" +#define STRING_space0 "space\0" +#define STRING_word0 "word\0" +#define STRING_xdigit "xdigit" + +#define STRING_DEFINE "DEFINE" + +#define STRING_CR_RIGHTPAR "CR)" +#define STRING_LF_RIGHTPAR "LF)" +#define STRING_CRLF_RIGHTPAR "CRLF)" +#define STRING_ANY_RIGHTPAR "ANY)" +#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" +#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" +#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" +#define STRING_UTF8_RIGHTPAR "UTF8)" + +#else /* SUPPORT_UTF8 */ + +/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This +works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode +only. */ + +#define CHAR_HT '\011' +#define CHAR_VT '\013' +#define CHAR_FF '\014' +#define CHAR_CR '\015' +#define CHAR_NL '\012' +#define CHAR_BS '\010' +#define CHAR_BEL '\007' +#define CHAR_ESC '\033' +#define CHAR_DEL '\177' + +#define CHAR_SPACE '\040' +#define CHAR_EXCLAMATION_MARK '\041' +#define CHAR_QUOTATION_MARK '\042' +#define CHAR_NUMBER_SIGN '\043' +#define CHAR_DOLLAR_SIGN '\044' +#define CHAR_PERCENT_SIGN '\045' +#define CHAR_AMPERSAND '\046' +#define CHAR_APOSTROPHE '\047' +#define CHAR_LEFT_PARENTHESIS '\050' +#define CHAR_RIGHT_PARENTHESIS '\051' +#define CHAR_ASTERISK '\052' +#define CHAR_PLUS '\053' +#define CHAR_COMMA '\054' +#define CHAR_MINUS '\055' +#define CHAR_DOT '\056' +#define CHAR_SLASH '\057' +#define CHAR_0 '\060' +#define CHAR_1 '\061' +#define CHAR_2 '\062' +#define CHAR_3 '\063' +#define CHAR_4 '\064' +#define CHAR_5 '\065' +#define CHAR_6 '\066' +#define CHAR_7 '\067' +#define CHAR_8 '\070' +#define CHAR_9 '\071' +#define CHAR_COLON '\072' +#define CHAR_SEMICOLON '\073' +#define CHAR_LESS_THAN_SIGN '\074' +#define CHAR_EQUALS_SIGN '\075' +#define CHAR_GREATER_THAN_SIGN '\076' +#define CHAR_QUESTION_MARK '\077' +#define CHAR_COMMERCIAL_AT '\100' +#define CHAR_A '\101' +#define CHAR_B '\102' +#define CHAR_C '\103' +#define CHAR_D '\104' +#define CHAR_E '\105' +#define CHAR_F '\106' +#define CHAR_G '\107' +#define CHAR_H '\110' +#define CHAR_I '\111' +#define CHAR_J '\112' +#define CHAR_K '\113' +#define CHAR_L '\114' +#define CHAR_M '\115' +#define CHAR_N '\116' +#define CHAR_O '\117' +#define CHAR_P '\120' +#define CHAR_Q '\121' +#define CHAR_R '\122' +#define CHAR_S '\123' +#define CHAR_T '\124' +#define CHAR_U '\125' +#define CHAR_V '\126' +#define CHAR_W '\127' +#define CHAR_X '\130' +#define CHAR_Y '\131' +#define CHAR_Z '\132' +#define CHAR_LEFT_SQUARE_BRACKET '\133' +#define CHAR_BACKSLASH '\134' +#define CHAR_RIGHT_SQUARE_BRACKET '\135' +#define CHAR_CIRCUMFLEX_ACCENT '\136' +#define CHAR_UNDERSCORE '\137' +#define CHAR_GRAVE_ACCENT '\140' +#define CHAR_a '\141' +#define CHAR_b '\142' +#define CHAR_c '\143' +#define CHAR_d '\144' +#define CHAR_e '\145' +#define CHAR_f '\146' +#define CHAR_g '\147' +#define CHAR_h '\150' +#define CHAR_i '\151' +#define CHAR_j '\152' +#define CHAR_k '\153' +#define CHAR_l '\154' +#define CHAR_m '\155' +#define CHAR_n '\156' +#define CHAR_o '\157' +#define CHAR_p '\160' +#define CHAR_q '\161' +#define CHAR_r '\162' +#define CHAR_s '\163' +#define CHAR_t '\164' +#define CHAR_u '\165' +#define CHAR_v '\166' +#define CHAR_w '\167' +#define CHAR_x '\170' +#define CHAR_y '\171' +#define CHAR_z '\172' +#define CHAR_LEFT_CURLY_BRACKET '\173' +#define CHAR_VERTICAL_LINE '\174' +#define CHAR_RIGHT_CURLY_BRACKET '\175' +#define CHAR_TILDE '\176' + +#define STR_HT "\011" +#define STR_VT "\013" +#define STR_FF "\014" +#define STR_CR "\015" +#define STR_NL "\012" +#define STR_BS "\010" +#define STR_BEL "\007" +#define STR_ESC "\033" +#define STR_DEL "\177" + +#define STR_SPACE "\040" +#define STR_EXCLAMATION_MARK "\041" +#define STR_QUOTATION_MARK "\042" +#define STR_NUMBER_SIGN "\043" +#define STR_DOLLAR_SIGN "\044" +#define STR_PERCENT_SIGN "\045" +#define STR_AMPERSAND "\046" +#define STR_APOSTROPHE "\047" +#define STR_LEFT_PARENTHESIS "\050" +#define STR_RIGHT_PARENTHESIS "\051" +#define STR_ASTERISK "\052" +#define STR_PLUS "\053" +#define STR_COMMA "\054" +#define STR_MINUS "\055" +#define STR_DOT "\056" +#define STR_SLASH "\057" +#define STR_0 "\060" +#define STR_1 "\061" +#define STR_2 "\062" +#define STR_3 "\063" +#define STR_4 "\064" +#define STR_5 "\065" +#define STR_6 "\066" +#define STR_7 "\067" +#define STR_8 "\070" +#define STR_9 "\071" +#define STR_COLON "\072" +#define STR_SEMICOLON "\073" +#define STR_LESS_THAN_SIGN "\074" +#define STR_EQUALS_SIGN "\075" +#define STR_GREATER_THAN_SIGN "\076" +#define STR_QUESTION_MARK "\077" +#define STR_COMMERCIAL_AT "\100" +#define STR_A "\101" +#define STR_B "\102" +#define STR_C "\103" +#define STR_D "\104" +#define STR_E "\105" +#define STR_F "\106" +#define STR_G "\107" +#define STR_H "\110" +#define STR_I "\111" +#define STR_J "\112" +#define STR_K "\113" +#define STR_L "\114" +#define STR_M "\115" +#define STR_N "\116" +#define STR_O "\117" +#define STR_P "\120" +#define STR_Q "\121" +#define STR_R "\122" +#define STR_S "\123" +#define STR_T "\124" +#define STR_U "\125" +#define STR_V "\126" +#define STR_W "\127" +#define STR_X "\130" +#define STR_Y "\131" +#define STR_Z "\132" +#define STR_LEFT_SQUARE_BRACKET "\133" +#define STR_BACKSLASH "\134" +#define STR_RIGHT_SQUARE_BRACKET "\135" +#define STR_CIRCUMFLEX_ACCENT "\136" +#define STR_UNDERSCORE "\137" +#define STR_GRAVE_ACCENT "\140" +#define STR_a "\141" +#define STR_b "\142" +#define STR_c "\143" +#define STR_d "\144" +#define STR_e "\145" +#define STR_f "\146" +#define STR_g "\147" +#define STR_h "\150" +#define STR_i "\151" +#define STR_j "\152" +#define STR_k "\153" +#define STR_l "\154" +#define STR_m "\155" +#define STR_n "\156" +#define STR_o "\157" +#define STR_p "\160" +#define STR_q "\161" +#define STR_r "\162" +#define STR_s "\163" +#define STR_t "\164" +#define STR_u "\165" +#define STR_v "\166" +#define STR_w "\167" +#define STR_x "\170" +#define STR_y "\171" +#define STR_z "\172" +#define STR_LEFT_CURLY_BRACKET "\173" +#define STR_VERTICAL_LINE "\174" +#define STR_RIGHT_CURLY_BRACKET "\175" +#define STR_TILDE "\176" + +#define STRING_ACCEPT0 STR_A STR_C STR_C STR_E STR_P STR_T "\0" +#define STRING_COMMIT0 STR_C STR_O STR_M STR_M STR_I STR_T "\0" +#define STRING_F0 STR_F "\0" +#define STRING_FAIL0 STR_F STR_A STR_I STR_L "\0" +#define STRING_PRUNE0 STR_P STR_R STR_U STR_N STR_E "\0" +#define STRING_SKIP0 STR_S STR_K STR_I STR_P "\0" +#define STRING_THEN STR_T STR_H STR_E STR_N + +#define STRING_alpha0 STR_a STR_l STR_p STR_h STR_a "\0" +#define STRING_lower0 STR_l STR_o STR_w STR_e STR_r "\0" +#define STRING_upper0 STR_u STR_p STR_p STR_e STR_r "\0" +#define STRING_alnum0 STR_a STR_l STR_n STR_u STR_m "\0" +#define STRING_ascii0 STR_a STR_s STR_c STR_i STR_i "\0" +#define STRING_blank0 STR_b STR_l STR_a STR_n STR_k "\0" +#define STRING_cntrl0 STR_c STR_n STR_t STR_r STR_l "\0" +#define STRING_digit0 STR_d STR_i STR_g STR_i STR_t "\0" +#define STRING_graph0 STR_g STR_r STR_a STR_p STR_h "\0" +#define STRING_print0 STR_p STR_r STR_i STR_n STR_t "\0" +#define STRING_punct0 STR_p STR_u STR_n STR_c STR_t "\0" +#define STRING_space0 STR_s STR_p STR_a STR_c STR_e "\0" +#define STRING_word0 STR_w STR_o STR_r STR_d "\0" +#define STRING_xdigit STR_x STR_d STR_i STR_g STR_i STR_t + +#define STRING_DEFINE STR_D STR_E STR_F STR_I STR_N STR_E + +#define STRING_CR_RIGHTPAR STR_C STR_R STR_RIGHT_PARENTHESIS +#define STRING_LF_RIGHTPAR STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS +#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS +#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS + +#endif /* SUPPORT_UTF8 */ + +/* Escape items that are just an encoding of a particular data value. */ #ifndef ESC_e -#define ESC_e 27 +#define ESC_e CHAR_ESC #endif #ifndef ESC_f -#define ESC_f '\f' +#define ESC_f CHAR_FF #endif #ifndef ESC_n -#define ESC_n NEWLINE +#define ESC_n CHAR_NL #endif #ifndef ESC_r -#define ESC_r '\r' +#define ESC_r CHAR_CR #endif /* We can't officially use ESC_t because it is a POSIX reserved identifier (presumably because of all the others like size_t). */ #ifndef ESC_tee -#define ESC_tee '\t' +#define ESC_tee CHAR_HT #endif /* Codes for different types of Unicode property */ @@ -496,22 +1186,28 @@ value such as \n. They must have non-zero values, as check_escape() returns their negation. Also, they must appear in the same order as in the opcode definitions below, up to ESC_z. There's a dummy for OP_ANY because it -corresponds to "." rather than an escape sequence. The final one must be -ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two -tests in the code for an escape greater than ESC_b and less than ESC_Z to -detect the types that may be repeated. These are the types that consume -characters. If any new escapes are put in between that don't consume a -character, that code will have to change. */ - -enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E, - ESC_Q, ESC_REF }; +corresponds to "." rather than an escape sequence, and another for OP_ALLANY +(which is used for [^] in JavaScript compatibility mode). -/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets -that extract substrings. Starting from 1 (i.e. after OP_END), the values up to +The final escape must be ESC_REF as subsequent values are used for +backreferences (\1, \2, \3, etc). There are two tests in the code for an escape +greater than ESC_b and less than ESC_Z to detect the types that may be +repeated. These are the types that consume characters. If any new escapes are +put in between that don't consume a character, that code will have to change. +*/ + +enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, + ESC_W, ESC_w, ESC_dum1, ESC_dum2, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, + ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_g, ESC_k, + ESC_REF }; + + +/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to OP_EOD must correspond in order to the list of escapes immediately above. -Note that whenever this list is updated, the two macro definitions that follow -must also be updated to match. */ + +*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions +that follow must also be updated to match. There is also a table called +"coptable" in pcre_dfa_exec.c that must be updated. */ enum { OP_END, /* 0 End of pattern */ @@ -520,141 +1216,181 @@ OP_SOD, /* 1 Start of data: \A */ OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_EXTUNI, /* 15 \X (extended Unicode sequence */ - OP_EODN, /* 16 End of data or \n at end of data: \Z. */ - OP_EOD, /* 17 End of data: \z */ - - OP_OPT, /* 18 Set runtime options */ - OP_CIRC, /* 19 Start of line - varies with multiline switch */ - OP_DOLL, /* 20 End of line - varies with multiline switch */ - OP_CHAR, /* 21 Match one character, casefully */ - OP_CHARNC, /* 22 Match one character, caselessly */ - OP_NOT, /* 23 Match one character, not the following one */ - - OP_STAR, /* 24 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */ - OP_PLUS, /* 26 the minimizing one second. */ - OP_MINPLUS, /* 27 This first set applies to single characters */ - OP_QUERY, /* 28 */ - OP_MINQUERY, /* 29 */ - OP_UPTO, /* 30 From 0 to n matches */ - OP_MINUPTO, /* 31 */ - OP_EXACT, /* 32 Exactly n matches */ - - OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */ - OP_NOTPLUS, /* 35 the minimizing one second. */ - OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */ - OP_NOTQUERY, /* 37 */ - OP_NOTMINQUERY, /* 38 */ - OP_NOTUPTO, /* 39 From 0 to n matches */ - OP_NOTMINUPTO, /* 40 */ - OP_NOTEXACT, /* 41 Exactly n matches */ - - OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 46 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 47 */ - OP_TYPEUPTO, /* 48 From 0 to n matches */ - OP_TYPEMINUPTO, /* 49 */ - OP_TYPEEXACT, /* 50 Exactly n matches */ - - OP_CRSTAR, /* 51 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 53 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_CRQUERY, /* 55 These are for character classes and back refs */ - OP_CRMINQUERY, /* 56 */ - OP_CRRANGE, /* 57 These are different to the three sets above. */ - OP_CRMINRANGE, /* 58 */ + OP_SET_SOM, /* 3 Set start of match (\K) */ + OP_NOT_WORD_BOUNDARY, /* 4 \B */ + OP_WORD_BOUNDARY, /* 5 \b */ + OP_NOT_DIGIT, /* 6 \D */ + OP_DIGIT, /* 7 \d */ + OP_NOT_WHITESPACE, /* 8 \S */ + OP_WHITESPACE, /* 9 \s */ + OP_NOT_WORDCHAR, /* 10 \W */ + OP_WORDCHAR, /* 11 \w */ + OP_ANY, /* 12 Match any character (subject to DOTALL) */ + OP_ALLANY, /* 13 Match any character (not subject to DOTALL) */ + OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 15 \P (not Unicode property) */ + OP_PROP, /* 16 \p (Unicode property) */ + OP_ANYNL, /* 17 \R (any newline sequence) */ + OP_NOT_HSPACE, /* 18 \H (not horizontal whitespace) */ + OP_HSPACE, /* 19 \h (horizontal whitespace) */ + OP_NOT_VSPACE, /* 20 \V (not vertical whitespace) */ + OP_VSPACE, /* 21 \v (vertical whitespace) */ + OP_EXTUNI, /* 22 \X (extended Unicode sequence */ + OP_EODN, /* 23 End of data or \n at end of data: \Z. */ + OP_EOD, /* 24 End of data: \z */ + + OP_OPT, /* 25 Set runtime options */ + OP_CIRC, /* 26 Start of line - varies with multiline switch */ + OP_DOLL, /* 27 End of line - varies with multiline switch */ + OP_CHAR, /* 28 Match one character, casefully */ + OP_CHARNC, /* 29 Match one character, caselessly */ + OP_NOT, /* 30 Match one character, not the following one */ + + OP_STAR, /* 31 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 32 these six opcodes must come in pairs, with */ + OP_PLUS, /* 33 the minimizing one second. */ + OP_MINPLUS, /* 34 This first set applies to single characters.*/ + OP_QUERY, /* 35 */ + OP_MINQUERY, /* 36 */ + + OP_UPTO, /* 37 From 0 to n matches */ + OP_MINUPTO, /* 38 */ + OP_EXACT, /* 39 Exactly n matches */ + + OP_POSSTAR, /* 40 Possessified star */ + OP_POSPLUS, /* 41 Possessified plus */ + OP_POSQUERY, /* 42 Posesssified query */ + OP_POSUPTO, /* 43 Possessified upto */ + + OP_NOTSTAR, /* 44 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 45 these six opcodes must come in pairs, with */ + OP_NOTPLUS, /* 46 the minimizing one second. They must be in */ + OP_NOTMINPLUS, /* 47 exactly the same order as those above. */ + OP_NOTQUERY, /* 48 This set applies to "not" single characters. */ + OP_NOTMINQUERY, /* 49 */ + + OP_NOTUPTO, /* 50 From 0 to n matches */ + OP_NOTMINUPTO, /* 51 */ + OP_NOTEXACT, /* 52 Exactly n matches */ + + OP_NOTPOSSTAR, /* 53 Possessified versions */ + OP_NOTPOSPLUS, /* 54 */ + OP_NOTPOSQUERY, /* 55 */ + OP_NOTPOSUPTO, /* 56 */ + + OP_TYPESTAR, /* 57 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 58 these six opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 59 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 60 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 61 This set applies to character types such as \d */ + OP_TYPEMINQUERY, /* 62 */ + + OP_TYPEUPTO, /* 63 From 0 to n matches */ + OP_TYPEMINUPTO, /* 64 */ + OP_TYPEEXACT, /* 65 Exactly n matches */ + + OP_TYPEPOSSTAR, /* 66 Possessified versions */ + OP_TYPEPOSPLUS, /* 67 */ + OP_TYPEPOSQUERY, /* 68 */ + OP_TYPEPOSUPTO, /* 69 */ + + OP_CRSTAR, /* 70 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 71 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 72 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 73 be in exactly the same order as those above. */ + OP_CRQUERY, /* 74 These are for character classes and back refs */ + OP_CRMINQUERY, /* 75 */ + OP_CRRANGE, /* 76 These are different to the three sets above. */ + OP_CRMINRANGE, /* 77 */ - OP_CLASS, /* 59 Match a character class, chars < 256 only */ - OP_NCLASS, /* 60 Same, but the bitmap was created from a negative + OP_CLASS, /* 78 Match a character class, chars < 256 only */ + OP_NCLASS, /* 79 Same, but the bitmap was created from a negative class - the difference is relevant only when a UTF-8 character > 255 is encountered. */ - OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the + OP_XCLASS, /* 80 Extended class for handling UTF-8 chars within the class. This does both positive and negative. */ - OP_REF, /* 62 Match a back reference */ - OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 64 Call out to external function if provided */ - - OP_ALT, /* 65 Start of alternation */ - OP_KET, /* 66 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 67 These two must remain together and in this */ - OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */ - - /* The assertions must come before ONCE and COND */ - - OP_ASSERT, /* 69 Positive lookahead */ - OP_ASSERT_NOT, /* 70 Negative lookahead */ - OP_ASSERTBACK, /* 71 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */ - OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */ - - /* ONCE and COND must come after the assertions, with ONCE first, as there's - a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* 74 Once matched, don't back up into the subpattern */ - OP_COND, /* 75 Conditional group */ - OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */ - - OP_BRAZERO, /* 77 These two must remain together and in this */ - OP_BRAMINZERO, /* 78 order. */ - - OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater - than can fit into an opcode. */ - - OP_BRA /* 80 This and greater values are used for brackets that - extract substrings up to EXTRACT_BASIC_MAX. After - that, use is made of OP_BRANUMBER. */ -}; + OP_REF, /* 81 Match a back reference */ + OP_RECURSE, /* 82 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 83 Call out to external function if provided */ + + OP_ALT, /* 84 Start of alternation */ + OP_KET, /* 85 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 86 These two must remain together and in this */ + OP_KETRMIN, /* 87 order. They are for groups the repeat for ever. */ + + /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ + + OP_ASSERT, /* 88 Positive lookahead */ + OP_ASSERT_NOT, /* 89 Negative lookahead */ + OP_ASSERTBACK, /* 90 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 91 Negative lookbehind */ + OP_REVERSE, /* 92 Move pointer back - used in lookbehind assertions */ -/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and -study.c that all opcodes are less than 128 in value. This makes handling UTF-8 -character sequences easier. */ - -/* The highest extraction number before we have to start using additional -bytes. (Originally PCRE didn't have support for extraction counts highter than -this number.) The value is limited by the number of opcodes left after OP_BRA, -i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional -opcodes. */ + /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, + as there's a test for >= ONCE for a subpattern that isn't an assertion. */ -#define EXTRACT_BASIC_MAX 100 + OP_ONCE, /* 93 Atomic group */ + OP_BRA, /* 94 Start of non-capturing bracket */ + OP_CBRA, /* 95 Start of capturing bracket */ + OP_COND, /* 96 Conditional group */ + + /* These three must follow the previous three, in the same order. There's a + check for >= SBRA to distinguish the two sets. */ + + OP_SBRA, /* 97 Start of non-capturing bracket, check empty */ + OP_SCBRA, /* 98 Start of capturing bracket, check empty */ + OP_SCOND, /* 99 Conditional group, check empty */ + + OP_CREF, /* 100 Used to hold a capture number as condition */ + OP_RREF, /* 101 Used to hold a recursion number as condition */ + OP_DEF, /* 102 The DEFINE condition */ + + OP_BRAZERO, /* 103 These two must remain together and in this */ + OP_BRAMINZERO, /* 104 order. */ + + /* These are backtracking control verbs */ + + OP_PRUNE, /* 105 */ + OP_SKIP, /* 106 */ + OP_THEN, /* 107 */ + OP_COMMIT, /* 108 */ + + /* These are forced failure and success verbs */ + + OP_FAIL, /* 109 */ + OP_ACCEPT, /* 110 */ + + /* This is used to skip a subpattern with a {0} quantifier */ + + OP_SKIPZERO /* 111 */ +}; /* This macro defines textual names for all the opcodes. These are used only for debugging. The macro is referenced only in pcre_printint.c. */ #define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "extuni", \ - "\\Z", "\\z", \ + "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ + "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte", \ + "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ + "extuni", "\\Z", "\\z", \ "Opt", "^", "$", "char", "charnc", "not", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ "*", "*?", "+", "+?", "?", "??", "{", "{", \ "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\ - "Brazero", "Braminzero", "Branumber", "Bra" + "AssertB", "AssertB not", "Reverse", \ + "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \ + "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \ + "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT", \ + "Skip zero" /* This macro defines the length of fixed length operations in the compiled @@ -668,9 +1404,11 @@ #define OP_LENGTHS \ 1, /* End */ \ - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ - 1, 1, /* Any, Anybyte */ \ + 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ + 1, 1, 1, /* Any, AllAny, Anybyte */ \ 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ 2, /* Char - the minimum length */ \ 2, /* Charnc - the minimum length */ \ @@ -678,12 +1416,15 @@ /* Positive single-char repeats ** These are */ \ 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ + 2, 2, 2, 4, /* *+, ++, ?+, upto+ */ \ /* Negative single-char repeats - only for chars < 256 */ \ 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ 4, 4, 4, /* NOT upto, minupto, exact */ \ + 2, 2, 2, 4, /* Possessive *, +, ?, upto */ \ /* Positive type repeats */ \ 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ 4, 4, 4, /* Type upto, minupto, exact */ \ + 2, 2, 2, 4, /* Possessive *+, ++, ?+, upto+ */ \ /* Character class & ref repeats */ \ 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ 5, 5, /* CRRANGE, CRMINRANGE */ \ @@ -702,17 +1443,24 @@ 1+LINK_SIZE, /* Assert behind */ \ 1+LINK_SIZE, /* Assert behind not */ \ 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* Once */ \ + 1+LINK_SIZE, /* ONCE */ \ + 1+LINK_SIZE, /* BRA */ \ + 3+LINK_SIZE, /* CBRA */ \ 1+LINK_SIZE, /* COND */ \ + 1+LINK_SIZE, /* SBRA */ \ + 3+LINK_SIZE, /* SCBRA */ \ + 1+LINK_SIZE, /* SCOND */ \ 3, /* CREF */ \ + 3, /* RREF */ \ + 1, /* DEF */ \ 1, 1, /* BRAZERO, BRAMINZERO */ \ - 3, /* BRANUMBER */ \ - 1+LINK_SIZE /* BRA */ \ + 1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \ + 1, 1, 1 /* FAIL, ACCEPT, SKIPZERO */ -/* A magic value for OP_CREF to indicate the "in recursion" condition. */ +/* A magic value for OP_RREF to indicate the "any recursion" condition. */ -#define CREF_RECURSE 0xffff +#define RREF_ANY 0xffff /* Error code numbers. They are given names so that they can more easily be tracked. */ @@ -722,7 +1470,8 @@ ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51 }; + ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, + ERR60, ERR61, ERR62, ERR63, ERR64 }; /* The real format of the start of the pcre block; the index of names and the code vector run on as long as necessary after the end. We store an explicit @@ -744,9 +1493,9 @@ typedef struct real_pcre { pcre_uint32 magic_number; pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - pcre_uint32 dummy1; /* For future use, maybe */ - + pcre_uint32 options; /* Public options */ + pcre_uint16 flags; /* Private flags */ + pcre_uint16 dummy1; /* For future use */ pcre_uint16 top_bracket; pcre_uint16 top_backref; pcre_uint16 first_byte; @@ -777,17 +1526,25 @@ const uschar *fcc; /* Points to case-flipping table */ const uschar *cbits; /* Points to character type table */ const uschar *ctypes; /* Points to table of type maps */ + const uschar *start_workspace;/* The start of working space */ const uschar *start_code; /* The start of the compiled code */ const uschar *start_pattern; /* The start of the pattern */ + const uschar *end_pattern; /* The end of the pattern */ + uschar *hwm; /* High watermark of workspace */ uschar *name_table; /* The name/number table */ int names_found; /* Number of entries so far */ int name_entry_size; /* Size of each entry */ + int bracount; /* Count of capturing parens as we compile */ + int final_bracount; /* Saved value after first pass */ int top_backref; /* Maximum back reference */ unsigned int backref_map; /* Bitmap of low back refs */ + int external_options; /* External (initial) options */ + int external_flags; /* External flag bits to be set */ int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL nopartial; /* Set TRUE if partial won't work */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + BOOL had_accept; /* (*ACCEPT) encountered */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed length */ } compile_data; /* Structure for maintaining a chain of pointers to the currently incomplete @@ -805,20 +1562,20 @@ struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ int group_num; /* Number of group that was called */ const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of md->start_match */ + USPTR save_start; /* Old value of mstart */ int *offset_save; /* Pointer to start of saved offsets */ int saved_max; /* Number of saved offsets */ } recursion_info; -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre_exec.c, close to the match() function, so that it is easy to keep it in -step with any changes of local variable. However, the pointer to the current -frame must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. NOTE: -This isn't used for a "normal" compilation of pcre. */ +/* Structure for building a chain of data for holding the values of the subject +pointer at the start of each subpattern, so as to detect when an empty string +has been matched by a subpattern - to break infinite loops. */ + +typedef struct eptrblock { + struct eptrblock *epb_prev; + USPTR epb_saved_eptr; +} eptrblock; -struct heapframe; /* Structure for passing "static" information around between the functions doing traditional NFA matching, so that they are thread-safe. */ @@ -830,29 +1587,33 @@ int *offset_vector; /* Offset vector */ int offset_end; /* One past the end */ int offset_max; /* The maximum usable for return data */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed */ const uschar *lcc; /* Points to lower casing table */ const uschar *ctypes; /* Points to table of type maps */ BOOL offset_overflow; /* Set if too many extractions */ BOOL notbol; /* NOTBOL flag */ BOOL noteol; /* NOTEOL flag */ BOOL utf8; /* UTF8 flag */ + BOOL jscript_compat; /* JAVASCRIPT_COMPAT flag */ BOOL endonly; /* Dollar not before final \n */ BOOL notempty; /* Empty string match not wanted */ BOOL partial; /* PARTIAL flag */ BOOL hitend; /* Hit the end of the subject at some point */ + BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ - USPTR start_match; /* Start of this match attempt */ + USPTR start_match_ptr; /* Start of matched string */ USPTR end_match_ptr; /* Subject position at end match */ int end_offset_top; /* Highwater mark at end of match */ int capture_last; /* Most recent capture number */ int start_offset; /* The start offset value */ + eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ + int eptrn; /* Next free eptrblock */ recursion_info *recursive; /* Linked list of recursion data */ void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ } match_data; /* A similar structure is used for the same purpose by the DFA matching @@ -865,8 +1626,9 @@ const uschar *tables; /* Character tables */ int moptions; /* Match options */ int poptions; /* Pattern options */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + uschar nl[4]; /* Newline string when fixed */ void *callout_data; /* To pass back to callouts */ } dfa_match_data; @@ -876,7 +1638,7 @@ #define ctype_letter 0x02 #define ctype_digit 0x04 #define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphameric or '_' */ +#define ctype_word 0x10 /* alphanumeric or '_' */ #define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ /* Offsets for the bitmap tables in pcre_cbits. Each table contains a set @@ -904,10 +1666,12 @@ #define tables_length (ctypes_offset + 256) /* Layout of the UCP type table that translates property names into types and -codes. */ +codes. Each entry used to point directly to a name, but to reduce the number of +relocations in shared libraries, it now has an offset into a single string +instead. */ typedef struct { - const char *name; + pcre_uint16 name_offset; pcre_uint16 type; pcre_uint16 value; } ucp_type_table; @@ -925,6 +1689,7 @@ extern const int _pcre_utf8_table1_size; +extern const char _pcre_utt_names[]; extern const ucp_type_table _pcre_utt[]; extern const int _pcre_utt_size; @@ -937,13 +1702,42 @@ one of the exported public functions. They have to be "external" in the C sense, but are not part of the PCRE public API. */ -extern int _pcre_ord2utf8(int, uschar *); -extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *, - const pcre_study_data *, pcre_study_data *); -extern int _pcre_ucp_findprop(const unsigned int, int *, int *); -extern int _pcre_ucp_othercase(const int); -extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_xclass(int, const uschar *); +extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, + int *, BOOL); +extern int _pcre_ord2utf8(int, uschar *); +extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, + const pcre_study_data *, pcre_study_data *); +extern int _pcre_valid_utf8(const uschar *, int); +extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, + int *, BOOL); +extern BOOL _pcre_xclass(int, const uschar *); + + +/* Unicode character database (UCD) */ + +typedef struct { + uschar script; + uschar chartype; + pcre_int32 other_case; +} ucd_record; + +extern const ucd_record _pcre_ucd_records[]; +extern const uschar _pcre_ucd_stage1[]; +extern const pcre_uint16 _pcre_ucd_stage2[]; +extern const int _pcre_ucp_gentype[]; + + +/* UCD access macros */ + +#define UCD_BLOCK_SIZE 128 +#define GET_UCD(ch) (_pcre_ucd_records + \ + _pcre_ucd_stage2[_pcre_ucd_stage1[(ch) / UCD_BLOCK_SIZE] * \ + UCD_BLOCK_SIZE + ch % UCD_BLOCK_SIZE]) + +#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype +#define UCD_SCRIPT(ch) GET_UCD(ch)->script +#define UCD_CATEGORY(ch) _pcre_ucp_gentype[UCD_CHARTYPE(ch)] +#define UCD_OTHERCASE(ch) (ch + GET_UCD(ch)->other_case) #endif Modified: freeswitch/trunk/libs/pcre/pcre_maketables.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_maketables.c (original) +++ freeswitch/trunk/libs/pcre/pcre_maketables.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -45,7 +45,10 @@ #ifndef DFTABLES -#include "pcre_internal.h" +# ifdef HAVE_CONFIG_H +# include "config.h" +# endif +# include "pcre_internal.h" #endif @@ -130,7 +133,7 @@ meta-character, which in this sense is any character that terminates a run of data characters. */ - if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; + if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; *p++ = x; } Added: freeswitch/trunk/libs/pcre/pcre_newline.c ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcre_newline.c Mon Jun 8 18:51:30 2009 @@ -0,0 +1,162 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2009 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains internal functions for testing newlines when more than +one kind of newline is to be recognized. When a newline is found, its length is +returned. In principle, we could implement several newline "types", each +referring to a different set of newline characters. At present, PCRE supports +only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, +and NLTYPE_ANY. The full list of Unicode newline characters is taken from +http://unicode.org/unicode/reports/tr18/. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + + +/************************************************* +* Check for newline at given position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is less than the end of the +string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + endptr pointer to the end of the string + lenptr where to return the length + utf8 TRUE if in utf8 mode + +Returns: TRUE or FALSE +*/ + +BOOL +_pcre_is_newline(USPTR ptr, int type, USPTR endptr, int *lenptr, BOOL utf8) +{ +int c; +if (utf8) { GETCHAR(c, ptr); } else c = *ptr; + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = 1; return TRUE; /* LF */ + case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; + return TRUE; /* CR */ + default: return FALSE; + } + +/* NLTYPE_ANY */ + +else switch(c) + { + case 0x000a: /* LF */ + case 0x000b: /* VT */ + case 0x000c: *lenptr = 1; return TRUE; /* FF */ + case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; + return TRUE; /* CR */ + case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ + default: return FALSE; + } +} + + + +/************************************************* +* Check for newline at previous position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is greater than the start of +the string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + startptr pointer to the start of the string + lenptr where to return the length + utf8 TRUE if in utf8 mode + +Returns: TRUE or FALSE +*/ + +BOOL +_pcre_was_newline(USPTR ptr, int type, USPTR startptr, int *lenptr, BOOL utf8) +{ +int c; +ptr--; +#ifdef SUPPORT_UTF8 +if (utf8) + { + BACKCHAR(ptr); + GETCHAR(c, ptr); + } +else c = *ptr; +#else /* no UTF-8 support */ +c = *ptr; +#endif /* SUPPORT_UTF8 */ + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; + return TRUE; /* LF */ + case 0x000d: *lenptr = 1; return TRUE; /* CR */ + default: return FALSE; + } + +else switch(c) + { + case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; + return TRUE; /* LF */ + case 0x000b: /* VT */ + case 0x000c: /* FF */ + case 0x000d: *lenptr = 1; return TRUE; /* CR */ + case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ + default: return FALSE; + } +} + +/* End of pcre_newline.c */ Modified: freeswitch/trunk/libs/pcre/pcre_ord2utf8.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_ord2utf8.c (original) +++ freeswitch/trunk/libs/pcre/pcre_ord2utf8.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -41,6 +41,9 @@ /* This file contains a private PCRE function that converts an ordinal character value into a UTF8 string. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif #include "pcre_internal.h" @@ -62,6 +65,7 @@ int _pcre_ord2utf8(int cvalue, uschar *buffer) { +#ifdef SUPPORT_UTF8 register int i, j; for (i = 0; i < _pcre_utf8_table1_size; i++) if (cvalue <= _pcre_utf8_table1[i]) break; @@ -73,6 +77,11 @@ } *buffer = _pcre_utf8_table2[i] | cvalue; return i + 1; +#else +(void)(cvalue); /* Keep compiler happy; this function won't ever be */ +(void)(buffer); /* called when SUPPORT_UTF8 is not defined. */ +return 0; +#endif } /* End of pcre_ord2utf8.c */ Modified: freeswitch/trunk/libs/pcre/pcre_printint.src ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_printint.src (original) +++ freeswitch/trunk/libs/pcre/pcre_printint.src Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2005 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -49,9 +49,23 @@ compiled regex for debugging purposes. */ +/* Macro that decides whether a character should be output as a literal or in +hexadecimal. We don't use isprint() because that can vary from system to system +(even without the use of locales) and we want the output always to be the same, +for testing purposes. This macro is used in pcretest as well as in this file. */ + +#ifdef EBCDIC +#define PRINTABLE(c) ((c) >= 64 && (c) < 255) +#else +#define PRINTABLE(c) ((c) >= 32 && (c) < 127) +#endif + +/* The table of operator names. */ + static const char *OP_names[] = { OP_NAME_LIST }; + /************************************************* * Print single- or multi-byte character * *************************************************/ @@ -61,9 +75,15 @@ { int c = *ptr; +#ifndef SUPPORT_UTF8 +utf8 = utf8; /* Avoid compiler warning */ +if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); +return 0; + +#else if (!utf8 || (c & 0xc0) != 0xc0) { - if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); + if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); return 0; } else @@ -92,6 +112,7 @@ if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); return a; } +#endif } @@ -105,11 +126,11 @@ { #ifdef SUPPORT_UCP int i; -for (i = _pcre_utt_size; i >= 0; i--) +for (i = _pcre_utt_size - 1; i >= 0; i--) { if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; } -return (i >= 0)? _pcre_utt[i].name : "??"; +return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??"; #else /* It gets harder and harder to shut off unwanted compiler warnings. */ ptype = ptype * pvalue; @@ -124,10 +145,13 @@ *************************************************/ /* Make this function work for a regex with integers either byte order. -However, we assume that what we are passed is a compiled regex. */ +However, we assume that what we are passed is a compiled regex. The +print_lengths flag controls whether offsets and lengths of items are printed. +They can be turned off from pcretest so that automatic tests on bytecode can be +written that do not depend on the value of LINK_SIZE. */ static void -pcre_printint(pcre *external_re, FILE *f) +pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) { real_pcre *re = (real_pcre *)external_re; uschar *codestart, *code; @@ -158,17 +182,10 @@ int c; int extra = 0; - fprintf(f, "%3d ", (int)(code - codestart)); - - if (*code >= OP_BRA) - { - if (*code - OP_BRA > EXTRACT_BASIC_MAX) - fprintf(f, "%3d Bra extra\n", GET(code, 1)); - else - fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA); - code += _pcre_OP_lengths[OP_BRA]; - continue; - } + if (print_lengths) + fprintf(f, "%3d ", (int)(code - codestart)); + else + fprintf(f, " "); switch(*code) { @@ -203,6 +220,15 @@ fprintf(f, "\n"); continue; + case OP_CBRA: + case OP_SCBRA: + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE)); + break; + + case OP_BRA: + case OP_SBRA: case OP_KETRMAX: case OP_KETRMIN: case OP_ALT: @@ -213,33 +239,47 @@ case OP_ASSERTBACK_NOT: case OP_ONCE: case OP_COND: + case OP_SCOND: case OP_REVERSE: - fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); break; - case OP_BRANUMBER: - printf("%3d %s", GET2(code, 1), OP_names[*code]); + case OP_CREF: + fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); break; - case OP_CREF: - if (GET2(code, 1) == CREF_RECURSE) - fprintf(f, " Cond recurse"); + case OP_RREF: + c = GET2(code, 1); + if (c == RREF_ANY) + fprintf(f, " Cond recurse any"); else - fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); + fprintf(f, " Cond recurse %d", c); + break; + + case OP_DEF: + fprintf(f, " Cond def"); break; case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: case OP_TYPESTAR: case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: case OP_TYPEPLUS: case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: case OP_TYPEQUERY: case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: fprintf(f, " "); if (*code >= OP_TYPESTAR) { @@ -257,17 +297,20 @@ case OP_EXACT: case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: fprintf(f, " "); extra = print_char(f, code+3, utf8); fprintf(f, "{"); - if (*code != OP_EXACT) fprintf(f, ","); + if (*code != OP_EXACT) fprintf(f, "0,"); fprintf(f, "%d}", GET2(code,1)); if (*code == OP_MINUPTO) fprintf(f, "?"); + else if (*code == OP_POSUPTO) fprintf(f, "+"); break; case OP_TYPEEXACT: case OP_TYPEUPTO: case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: fprintf(f, " %s", OP_names[code[3]]); if (code[3] == OP_PROP || code[3] == OP_NOTPROP) { @@ -278,20 +321,26 @@ if (*code != OP_TYPEEXACT) fprintf(f, "0,"); fprintf(f, "%d}", GET2(code,1)); if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); + else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+"); break; case OP_NOT: - if (isprint(c = code[1])) fprintf(f, " [^%c]", c); + c = code[1]; + if (PRINTABLE(c)) fprintf(f, " [^%c]", c); else fprintf(f, " [^\\x%02x]", c); break; case OP_NOTSTAR: case OP_NOTMINSTAR: + case OP_NOTPOSSTAR: case OP_NOTPLUS: case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: case OP_NOTQUERY: case OP_NOTMINQUERY: - if (isprint(c = code[1])) fprintf(f, " [^%c]", c); + case OP_NOTPOSQUERY: + c = code[1]; + if (PRINTABLE(c)) fprintf(f, " [^%c]", c); else fprintf(f, " [^\\x%02x]", c); fprintf(f, "%s", OP_names[*code]); break; @@ -299,15 +348,20 @@ case OP_NOTEXACT: case OP_NOTUPTO: case OP_NOTMINUPTO: - if (isprint(c = code[3])) fprintf(f, " [^%c]{", c); + case OP_NOTPOSUPTO: + c = code[3]; + if (PRINTABLE(c)) fprintf(f, " [^%c]{", c); else fprintf(f, " [^\\x%02x]{", c); if (*code != OP_NOTEXACT) fprintf(f, "0,"); fprintf(f, "%d}", GET2(code,1)); if (*code == OP_NOTMINUPTO) fprintf(f, "?"); + else if (*code == OP_NOTPOSUPTO) fprintf(f, "+"); break; case OP_RECURSE: - fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); break; case OP_REF: @@ -363,12 +417,14 @@ for (j = i+1; j < 256; j++) if ((ccode[j/8] & (1 << (j&7))) == 0) break; if (i == '-' || i == ']') fprintf(f, "\\"); - if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i); + if (PRINTABLE(i)) fprintf(f, "%c", i); + else fprintf(f, "\\x%02x", i); if (--j > i) { if (j != i + 1) fprintf(f, "-"); if (j == '-' || j == ']') fprintf(f, "\\"); - if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j); + if (PRINTABLE(j)) fprintf(f, "%c", j); + else fprintf(f, "\\x%02x", j); } i = j; } Modified: freeswitch/trunk/libs/pcre/pcre_refcount.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_refcount.c (original) +++ freeswitch/trunk/libs/pcre/pcre_refcount.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -43,6 +43,11 @@ pattern data block. This might be helpful in applications where the block is shared by different users. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -63,7 +68,7 @@ a negative error number */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION pcre_refcount(pcre *argument_re, int adjust) { real_pcre *re = (real_pcre *)argument_re; Modified: freeswitch/trunk/libs/pcre/pcre_scanner.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_scanner.cc (original) +++ freeswitch/trunk/libs/pcre/pcre_scanner.cc Mon Jun 8 18:51:30 2009 @@ -29,9 +29,14 @@ // // Author: Sanjay Ghemawat +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <vector> #include <assert.h> -#include "config.h" + +#include "pcrecpp_internal.h" #include "pcre_scanner.h" using std::vector; @@ -43,6 +48,7 @@ input_(data_), skip_(NULL), should_skip_(false), + skip_repeat_(false), save_comments_(false), comments_(NULL), comments_offset_(0) { @@ -53,6 +59,7 @@ input_(data_), skip_(NULL), should_skip_(false), + skip_repeat_(false), save_comments_(false), comments_(NULL), comments_offset_(0) { @@ -63,15 +70,31 @@ delete comments_; } +void Scanner::SetSkipExpression(const char* re) { + delete skip_; + if (re != NULL) { + skip_ = new RE(re); + should_skip_ = true; + skip_repeat_ = true; + ConsumeSkip(); + } else { + skip_ = NULL; + should_skip_ = false; + skip_repeat_ = false; + } +} + void Scanner::Skip(const char* re) { delete skip_; if (re != NULL) { skip_ = new RE(re); should_skip_ = true; + skip_repeat_ = false; ConsumeSkip(); } else { skip_ = NULL; should_skip_ = false; + skip_repeat_ = false; } } @@ -118,19 +141,22 @@ // helper function to consume *skip_ and honour save_comments_ void Scanner::ConsumeSkip() { + const char* start_data = input_.data(); + while (skip_->Consume(&input_)) { + if (!skip_repeat_) { + // Only one skip allowed. + break; + } + } if (save_comments_) { - if (NULL == comments_) { + if (comments_ == NULL) { comments_ = new vector<StringPiece>; } - const char *start_data = input_.data(); - skip_->Consume(&input_); // already pointing one past end, so no need to +1 int length = input_.data() - start_data; if (length > 0) { comments_->push_back(StringPiece(start_data, length)); } - } else { - skip_->Consume(&input_); } } Modified: freeswitch/trunk/libs/pcre/pcre_scanner.h ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_scanner.h (original) +++ freeswitch/trunk/libs/pcre/pcre_scanner.h Mon Jun 8 18:51:30 2009 @@ -36,7 +36,7 @@ // Scanner scanner(input); // string var; // int number; -// scanner.Skip("\\s+"); // Skip any white space we encounter +// scanner.SetSkipExpression("\\s+"); // Skip any white space we encounter // while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) { // ...; // } @@ -47,12 +47,13 @@ #include <assert.h> #include <string> #include <vector> + #include <pcrecpp.h> #include <pcre_stringpiece.h> namespace pcrecpp { -class Scanner { +class PCRECPP_EXP_DEFN Scanner { public: Scanner(); explicit Scanner(const std::string& input); @@ -79,9 +80,9 @@ // If it returns true, it skips over the matched input and any // following input that matches the "skip" regular expression. bool Consume(const RE& re, - const Arg& arg0 = no_arg, - const Arg& arg1 = no_arg, - const Arg& arg2 = no_arg + const Arg& arg0 = RE::no_arg, + const Arg& arg1 = RE::no_arg, + const Arg& arg2 = RE::no_arg // TODO: Allow more arguments? ); @@ -90,10 +91,16 @@ // skipped. For example, a programming language scanner would use // a skip RE that matches white space and comments. // - // scanner.Skip("(\\s|//.*|/[*](.|\n)*?[*]/)*"); + // scanner.SetSkipExpression("\\s+|//.*|/[*](.|\n)*?[*]/"); + // + // Skipping repeats as long as it succeeds. We used to let people do + // this by writing "(...)*" in the regular expression, but that added + // up to lots of recursive calls within the pcre library, so now we + // control repetition explicitly via the function call API. // // You can pass NULL for "re" if you do not want any data to be skipped. - void Skip(const char* re); + void Skip(const char* re); // DEPRECATED; does *not* repeat + void SetSkipExpression(const char* re); // Temporarily pause "skip"ing. This // Skip("Foo"); code ; DisableSkip(); code; EnableSkip() @@ -109,12 +116,13 @@ /***** Special wrappers around SetSkip() for some common idioms *****/ // Arranges to skip whitespace, C comments, C++ comments. - // The overall RE is a repeated disjunction of the following REs: + // The overall RE is a disjunction of the following REs: // \\s whitespace // //.*\n C++ comment // /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x) + // We get repetition via the semantics of SetSkipExpression, not by using * void SkipCXXComments() { - Skip("((\\s|//.*\n|/[*](.|\n)*?[*]/)*)"); + SetSkipExpression("\\s|//.*\n|/[*](?:\n|.)*?[*]/"); } void set_save_comments(bool comments) { @@ -143,6 +151,7 @@ StringPiece input_; // Unprocessed input RE* skip_; // If non-NULL, RE for skipping input bool should_skip_; // If true, use skip_ + bool skip_repeat_; // If true, repeat skip_ as long as it works bool save_comments_; // If true, aggregate the skip expression // the skipped comments Modified: freeswitch/trunk/libs/pcre/pcre_scanner_unittest.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_scanner_unittest.cc (original) +++ freeswitch/trunk/libs/pcre/pcre_scanner_unittest.cc Mon Jun 8 18:51:30 2009 @@ -32,10 +32,19 @@ // Unittest for scanner, especially GetNextComments and GetComments() // functionality. +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <stdio.h> +#include <string> #include <vector> -#include <pcre_stringpiece.h> -#include <pcre_scanner.h> + +#include "pcrecpp.h" +#include "pcre_stringpiece.h" +#include "pcre_scanner.h" + +#define FLAGS_unittest_stack_size 49152 // Dies with a fatal error if the two values are not equal. #define CHECK_EQ(a, b) do { \ @@ -116,8 +125,31 @@ comments.resize(0); } +static void TestBigComment() { + string input; + for (int i = 0; i < 1024; ++i) { + char buf[1024]; // definitely big enough + sprintf(buf, " # Comment %d\n", i); + input += buf; + } + input += "name = value;\n"; + + Scanner s(input.c_str()); + s.SetSkipExpression("\\s+|#.*\n"); + + string name; + string value; + s.Consume("(\\w+) = (\\w+);", &name, &value); + CHECK_EQ(name, "name"); + CHECK_EQ(value, "value"); +} + +// TODO: also test scanner and big-comment in a thread with a +// small stack size + int main(int argc, char** argv) { TestScanner(); + TestBigComment(); // Done printf("OK\n"); Modified: freeswitch/trunk/libs/pcre/pcre_stringpiece.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_stringpiece.cc (original) +++ freeswitch/trunk/libs/pcre/pcre_stringpiece.cc Mon Jun 8 18:51:30 2009 @@ -30,8 +30,12 @@ // Author: wilsonh@google.com (Wilson Hsieh) // -#include <iostream> +#ifdef HAVE_CONFIG_H #include "config.h" +#endif + +#include <iostream> +#include "pcrecpp_internal.h" #include "pcre_stringpiece.h" std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) { Modified: freeswitch/trunk/libs/pcre/pcre_stringpiece.h.in ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_stringpiece.h.in (original) +++ freeswitch/trunk/libs/pcre/pcre_stringpiece.h.in Mon Jun 8 18:51:30 2009 @@ -50,11 +50,13 @@ #include <bits/type_traits.h> #endif +#include <pcre.h> + using std::string; namespace pcrecpp { -class StringPiece { +class PCRECPP_EXP_DEFN StringPiece { private: const char* ptr_; int length_; @@ -66,7 +68,10 @@ StringPiece() : ptr_(NULL), length_(0) { } StringPiece(const char* str) - : ptr_(str), length_(static_cast<int>(strlen(str))) { } + : ptr_(str), length_(static_cast<int>(strlen(ptr_))) { } + StringPiece(const unsigned char* str) + : ptr_(reinterpret_cast<const char*>(str)), + length_(static_cast<int>(strlen(ptr_))) { } StringPiece(const string& str) : ptr_(str.data()), length_(static_cast<int>(str.size())) { } StringPiece(const char* offset, int len) Modified: freeswitch/trunk/libs/pcre/pcre_stringpiece_unittest.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_stringpiece_unittest.cc (original) +++ freeswitch/trunk/libs/pcre/pcre_stringpiece_unittest.cc Mon Jun 8 18:51:30 2009 @@ -1,10 +1,16 @@ // Copyright 2003 and onwards Google Inc. // Author: Sanjay Ghemawat +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <stdio.h> #include <map> #include <algorithm> // for make_pair -#include <pcre_stringpiece.h> + +#include "pcrecpp.h" +#include "pcre_stringpiece.h" // CHECK dies with a fatal error if condition is not true. It is *not* // controlled by NDEBUG, so the check will be executed regardless of Modified: freeswitch/trunk/libs/pcre/pcre_study.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_study.c (original) +++ freeswitch/trunk/libs/pcre/pcre_study.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,9 +42,18 @@ supporting functions. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" +/* Returns from set_start_bits() */ + +enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE }; + + /************************************************* * Set a bit and maybe its alternate case * *************************************************/ @@ -72,12 +81,16 @@ /************************************************* -* Create bitmap of starting chars * +* Create bitmap of starting bytes * *************************************************/ -/* This function scans a compiled unanchored expression and attempts to build a -bitmap of the set of initial characters. If it can't, it returns FALSE. As time -goes by, we may be able to get more clever at doing this. +/* This function scans a compiled unanchored expression recursively and +attempts to build a bitmap of the set of possible starting bytes. As time goes +by, we may be able to get more clever at doing this. The SSB_CONTINUE return is +useful for parenthesized groups in patterns such as (a*)b where the group +provides some optional starting bytes but scanning must continue at the outer +level to find at least one mandatory byte. At the outermost level, this +function fails unless the result is SSB_DONE. Arguments: code points to an expression @@ -86,14 +99,17 @@ utf8 TRUE if in UTF-8 mode cd the block with char table pointers -Returns: TRUE if table built, FALSE otherwise +Returns: SSB_FAIL => Failed to find any starting bytes + SSB_DONE => Found mandatory starting bytes + SSB_CONTINUE => Found optional starting bytes */ -static BOOL +static int set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, BOOL utf8, compile_data *cd) { register int c; +int yield = SSB_DONE; #if 0 /* ========================================================================= */ @@ -114,36 +130,60 @@ do { - const uschar *tcode = code + 1 + LINK_SIZE; + const uschar *tcode = code + (((int)*code == OP_CBRA)? 3:1) + LINK_SIZE; BOOL try_next = TRUE; - while (try_next) + while (try_next) /* Loop for items in this branch */ { - /* If a branch starts with a bracket or a positive lookahead assertion, - recurse to set bits from within them. That's all for this branch. */ - - if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) + int rc; + switch(*tcode) { - if (!set_start_bits(tcode, start_bits, caseless, utf8, cd)) - return FALSE; - try_next = FALSE; - } + /* Fail if we reach something we don't understand */ - else switch(*tcode) - { default: - return FALSE; + return SSB_FAIL; - /* Skip over callout */ + /* If we hit a bracket or a positive lookahead assertion, recurse to set + bits from within the subpattern. If it can't find anything, we have to + give up. If it finds some mandatory character(s), we are done for this + branch. Otherwise, carry on scanning after the subpattern. */ + + case OP_BRA: + case OP_SBRA: + case OP_CBRA: + case OP_SCBRA: + case OP_ONCE: + case OP_ASSERT: + rc = set_start_bits(tcode, start_bits, caseless, utf8, cd); + if (rc == SSB_FAIL) return SSB_FAIL; + if (rc == SSB_DONE) try_next = FALSE; else + { + do tcode += GET(tcode, 1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + } + break; - case OP_CALLOUT: - tcode += 2 + 2*LINK_SIZE; + /* If we hit ALT or KET, it means we haven't found anything mandatory in + this branch, though we might have found something optional. For ALT, we + continue with the next alternative, but we have to arrange that the final + result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, + return SSB_CONTINUE: if this is the top level, that indicates failure, + but after a nested subpattern, it causes scanning to continue. */ + + case OP_ALT: + yield = SSB_CONTINUE; + try_next = FALSE; break; - /* Skip over extended extraction bracket number */ + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + return SSB_CONTINUE; - case OP_BRANUMBER: - tcode += 3; + /* Skip over callout */ + + case OP_CALLOUT: + tcode += 2 + 2*LINK_SIZE; break; /* Skip over lookbehind and negative lookahead assertions */ @@ -152,7 +192,7 @@ case OP_ASSERTBACK: case OP_ASSERTBACK_NOT: do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1+LINK_SIZE; + tcode += 1 + LINK_SIZE; break; /* Skip over an option setting, changing the caseless flag */ @@ -166,27 +206,38 @@ case OP_BRAZERO: case OP_BRAMINZERO: - if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd)) - return FALSE; + if (set_start_bits(++tcode, start_bits, caseless, utf8, cd) == SSB_FAIL) + return SSB_FAIL; /* ========================================================================= See the comment at the head of this function concerning the next line, which was an old fudge for the benefit of OS/2. dummy = 1; ========================================================================= */ do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1+LINK_SIZE; + tcode += 1 + LINK_SIZE; + break; + + /* SKIPZERO skips the bracket. */ + + case OP_SKIPZERO: + tcode++; + do tcode += GET(tcode,1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; break; /* Single-char * or ? sets the bit and tries the next item */ case OP_STAR: case OP_MINSTAR: + case OP_POSSTAR: case OP_QUERY: case OP_MINQUERY: + case OP_POSQUERY: set_bit(start_bits, tcode[1], caseless, cd); tcode += 2; #ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; + if (utf8 && tcode[-1] >= 0xc0) + tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; #endif break; @@ -194,10 +245,12 @@ case OP_UPTO: case OP_MINUPTO: + case OP_POSUPTO: set_bit(start_bits, tcode[3], caseless, cd); tcode += 4; #ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; + if (utf8 && tcode[-1] >= 0xc0) + tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; #endif break; @@ -210,6 +263,7 @@ case OP_CHARNC: case OP_PLUS: case OP_MINPLUS: + case OP_POSPLUS: set_bit(start_bits, tcode[1], caseless, cd); try_next = FALSE; break; @@ -283,16 +337,20 @@ case OP_TYPEUPTO: case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: tcode += 2; /* Fall through */ case OP_TYPESTAR: case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: case OP_TYPEQUERY: case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: switch(tcode[1]) { case OP_ANY: - return FALSE; + case OP_ALLANY: + return SSB_FAIL; case OP_NOT_DIGIT: for (c = 0; c < 32; c++) @@ -349,11 +407,13 @@ character with a value > 255. */ case OP_NCLASS: +#ifdef SUPPORT_UTF8 if (utf8) { start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ } +#endif /* Fall through */ case OP_CLASS: @@ -366,6 +426,7 @@ value is > 127. In fact, there are only two possible starting bytes for characters in the range 128 - 255. */ +#ifdef SUPPORT_UTF8 if (utf8) { for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; @@ -383,6 +444,7 @@ /* In non-UTF-8 mode, the two bit maps are completely compatible. */ else +#endif { for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; } @@ -418,7 +480,7 @@ code += GET(code, 1); /* Advance to next branch */ } while (*code == OP_ALT); -return TRUE; +return yield; } @@ -442,7 +504,7 @@ NULL on error or if no optimization possible */ -PCRE_DATA_SCOPE pcre_extra * +PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION pcre_study(const pcre *external_re, int options, const char **errorptr) { uschar start_bits[32]; @@ -474,7 +536,8 @@ a multiline pattern that matches only at "line starts", no further processing at present. */ -if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) +if ((re->options & PCRE_ANCHORED) != 0 || + (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) return NULL; /* Set the character tables in the block that is passed around */ @@ -492,8 +555,8 @@ /* See if we can find a fixed set of initial characters for the pattern. */ memset(start_bits, 0, 32 * sizeof(uschar)); -if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, - (re->options & PCRE_UTF8) != 0, &compile_block)) return NULL; +if (set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, + (re->options & PCRE_UTF8) != 0, &compile_block) != SSB_DONE) return NULL; /* Get a pcre_extra block and a pcre_study_data block. The study data is put in the latter, which is pointed to by the former, which may also get additional Modified: freeswitch/trunk/libs/pcre/pcre_tables.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_tables.c (original) +++ freeswitch/trunk/libs/pcre/pcre_tables.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -44,6 +44,10 @@ clashes with the library. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -61,6 +65,8 @@ /* These are the breakpoints for different numbers of bytes in a UTF-8 character. */ +#ifdef SUPPORT_UTF8 + const int _pcre_utf8_table1[] = { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; @@ -72,9 +78,8 @@ const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; -/* Table of the number of extra characters, indexed by the first character -masked with 0x3f. The highest number for a valid UTF-8 character is in fact -0x3d. */ +/* Table of the number of extra bytes, indexed by the first byte masked with +0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ const uschar _pcre_utf8_table4[] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, @@ -82,112 +87,392 @@ 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; -/* This table translates Unicode property names into type and code values. It -is searched by binary chop, so must be in collating sequence of name. */ +/* Table to translate from particular type value to the general value. */ + +const int _pcre_ucp_gentype[] = { + ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ + ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ + ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ + ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ + ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ + ucp_P, ucp_P, /* Ps, Po */ + ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ + ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ +}; + +/* The pcre_utt[] table below translates Unicode property names into type and +code values. It is searched by binary chop, so must be in collating sequence of +name. Originally, the table contained pointers to the name strings in the first +field of each entry. However, that leads to a large number of relocations when +a shared library is dynamically loaded. A significant reduction is made by +putting all the names into a single, large string and then using offsets in the +table itself. Maintenance is more error-prone, but frequent changes to this +data are unlikely. + +July 2008: There is now a script called maint/GenerateUtt.py that can be used +to generate this data instead of maintaining it entirely by hand. + +The script was updated in March 2009 to generate a new EBCDIC-compliant +version. Like all other character and string literals that are compared against +the regular expression pattern, we must use STR_ macros instead of literal +strings to make sure that UTF-8 support works on EBCDIC platforms. */ + +#define STRING_Any0 STR_A STR_n STR_y "\0" +#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" +#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" +#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" +#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" +#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" +#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" +#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" +#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" +#define STRING_C0 STR_C "\0" +#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" +#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" +#define STRING_Cc0 STR_C STR_c "\0" +#define STRING_Cf0 STR_C STR_f "\0" +#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" +#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" +#define STRING_Cn0 STR_C STR_n "\0" +#define STRING_Co0 STR_C STR_o "\0" +#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" +#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" +#define STRING_Cs0 STR_C STR_s "\0" +#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" +#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" +#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" +#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" +#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" +#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" +#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" +#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" +#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" +#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" +#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" +#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" +#define STRING_Han0 STR_H STR_a STR_n "\0" +#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" +#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" +#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" +#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" +#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" +#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" +#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" +#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" +#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" +#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" +#define STRING_L0 STR_L "\0" +#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" +#define STRING_Lao0 STR_L STR_a STR_o "\0" +#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" +#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" +#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" +#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" +#define STRING_Ll0 STR_L STR_l "\0" +#define STRING_Lm0 STR_L STR_m "\0" +#define STRING_Lo0 STR_L STR_o "\0" +#define STRING_Lt0 STR_L STR_t "\0" +#define STRING_Lu0 STR_L STR_u "\0" +#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" +#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" +#define STRING_M0 STR_M "\0" +#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" +#define STRING_Mc0 STR_M STR_c "\0" +#define STRING_Me0 STR_M STR_e "\0" +#define STRING_Mn0 STR_M STR_n "\0" +#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" +#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" +#define STRING_N0 STR_N "\0" +#define STRING_Nd0 STR_N STR_d "\0" +#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" +#define STRING_Nko0 STR_N STR_k STR_o "\0" +#define STRING_Nl0 STR_N STR_l "\0" +#define STRING_No0 STR_N STR_o "\0" +#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" +#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" +#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" +#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" +#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" +#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" +#define STRING_P0 STR_P "\0" +#define STRING_Pc0 STR_P STR_c "\0" +#define STRING_Pd0 STR_P STR_d "\0" +#define STRING_Pe0 STR_P STR_e "\0" +#define STRING_Pf0 STR_P STR_f "\0" +#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" +#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" +#define STRING_Pi0 STR_P STR_i "\0" +#define STRING_Po0 STR_P STR_o "\0" +#define STRING_Ps0 STR_P STR_s "\0" +#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" +#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" +#define STRING_S0 STR_S "\0" +#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" +#define STRING_Sc0 STR_S STR_c "\0" +#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" +#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" +#define STRING_Sk0 STR_S STR_k "\0" +#define STRING_Sm0 STR_S STR_m "\0" +#define STRING_So0 STR_S STR_o "\0" +#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" +#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" +#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" +#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" +#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" +#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" +#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" +#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" +#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" +#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" +#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" +#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" +#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" +#define STRING_Vai0 STR_V STR_a STR_i "\0" +#define STRING_Yi0 STR_Y STR_i "\0" +#define STRING_Z0 STR_Z "\0" +#define STRING_Zl0 STR_Z STR_l "\0" +#define STRING_Zp0 STR_Z STR_p "\0" +#define STRING_Zs0 STR_Z STR_s "\0" + +const char _pcre_utt_names[] = + STRING_Any0 + STRING_Arabic0 + STRING_Armenian0 + STRING_Balinese0 + STRING_Bengali0 + STRING_Bopomofo0 + STRING_Braille0 + STRING_Buginese0 + STRING_Buhid0 + STRING_C0 + STRING_Canadian_Aboriginal0 + STRING_Carian0 + STRING_Cc0 + STRING_Cf0 + STRING_Cham0 + STRING_Cherokee0 + STRING_Cn0 + STRING_Co0 + STRING_Common0 + STRING_Coptic0 + STRING_Cs0 + STRING_Cuneiform0 + STRING_Cypriot0 + STRING_Cyrillic0 + STRING_Deseret0 + STRING_Devanagari0 + STRING_Ethiopic0 + STRING_Georgian0 + STRING_Glagolitic0 + STRING_Gothic0 + STRING_Greek0 + STRING_Gujarati0 + STRING_Gurmukhi0 + STRING_Han0 + STRING_Hangul0 + STRING_Hanunoo0 + STRING_Hebrew0 + STRING_Hiragana0 + STRING_Inherited0 + STRING_Kannada0 + STRING_Katakana0 + STRING_Kayah_Li0 + STRING_Kharoshthi0 + STRING_Khmer0 + STRING_L0 + STRING_L_AMPERSAND0 + STRING_Lao0 + STRING_Latin0 + STRING_Lepcha0 + STRING_Limbu0 + STRING_Linear_B0 + STRING_Ll0 + STRING_Lm0 + STRING_Lo0 + STRING_Lt0 + STRING_Lu0 + STRING_Lycian0 + STRING_Lydian0 + STRING_M0 + STRING_Malayalam0 + STRING_Mc0 + STRING_Me0 + STRING_Mn0 + STRING_Mongolian0 + STRING_Myanmar0 + STRING_N0 + STRING_Nd0 + STRING_New_Tai_Lue0 + STRING_Nko0 + STRING_Nl0 + STRING_No0 + STRING_Ogham0 + STRING_Ol_Chiki0 + STRING_Old_Italic0 + STRING_Old_Persian0 + STRING_Oriya0 + STRING_Osmanya0 + STRING_P0 + STRING_Pc0 + STRING_Pd0 + STRING_Pe0 + STRING_Pf0 + STRING_Phags_Pa0 + STRING_Phoenician0 + STRING_Pi0 + STRING_Po0 + STRING_Ps0 + STRING_Rejang0 + STRING_Runic0 + STRING_S0 + STRING_Saurashtra0 + STRING_Sc0 + STRING_Shavian0 + STRING_Sinhala0 + STRING_Sk0 + STRING_Sm0 + STRING_So0 + STRING_Sundanese0 + STRING_Syloti_Nagri0 + STRING_Syriac0 + STRING_Tagalog0 + STRING_Tagbanwa0 + STRING_Tai_Le0 + STRING_Tamil0 + STRING_Telugu0 + STRING_Thaana0 + STRING_Thai0 + STRING_Tibetan0 + STRING_Tifinagh0 + STRING_Ugaritic0 + STRING_Vai0 + STRING_Yi0 + STRING_Z0 + STRING_Zl0 + STRING_Zp0 + STRING_Zs0; const ucp_type_table _pcre_utt[] = { - { "Any", PT_ANY, 0 }, - { "Arabic", PT_SC, ucp_Arabic }, - { "Armenian", PT_SC, ucp_Armenian }, - { "Bengali", PT_SC, ucp_Bengali }, - { "Bopomofo", PT_SC, ucp_Bopomofo }, - { "Braille", PT_SC, ucp_Braille }, - { "Buginese", PT_SC, ucp_Buginese }, - { "Buhid", PT_SC, ucp_Buhid }, - { "C", PT_GC, ucp_C }, - { "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal }, - { "Cc", PT_PC, ucp_Cc }, - { "Cf", PT_PC, ucp_Cf }, - { "Cherokee", PT_SC, ucp_Cherokee }, - { "Cn", PT_PC, ucp_Cn }, - { "Co", PT_PC, ucp_Co }, - { "Common", PT_SC, ucp_Common }, - { "Coptic", PT_SC, ucp_Coptic }, - { "Cs", PT_PC, ucp_Cs }, - { "Cypriot", PT_SC, ucp_Cypriot }, - { "Cyrillic", PT_SC, ucp_Cyrillic }, - { "Deseret", PT_SC, ucp_Deseret }, - { "Devanagari", PT_SC, ucp_Devanagari }, - { "Ethiopic", PT_SC, ucp_Ethiopic }, - { "Georgian", PT_SC, ucp_Georgian }, - { "Glagolitic", PT_SC, ucp_Glagolitic }, - { "Gothic", PT_SC, ucp_Gothic }, - { "Greek", PT_SC, ucp_Greek }, - { "Gujarati", PT_SC, ucp_Gujarati }, - { "Gurmukhi", PT_SC, ucp_Gurmukhi }, - { "Han", PT_SC, ucp_Han }, - { "Hangul", PT_SC, ucp_Hangul }, - { "Hanunoo", PT_SC, ucp_Hanunoo }, - { "Hebrew", PT_SC, ucp_Hebrew }, - { "Hiragana", PT_SC, ucp_Hiragana }, - { "Inherited", PT_SC, ucp_Inherited }, - { "Kannada", PT_SC, ucp_Kannada }, - { "Katakana", PT_SC, ucp_Katakana }, - { "Kharoshthi", PT_SC, ucp_Kharoshthi }, - { "Khmer", PT_SC, ucp_Khmer }, - { "L", PT_GC, ucp_L }, - { "L&", PT_LAMP, 0 }, - { "Lao", PT_SC, ucp_Lao }, - { "Latin", PT_SC, ucp_Latin }, - { "Limbu", PT_SC, ucp_Limbu }, - { "Linear_B", PT_SC, ucp_Linear_B }, - { "Ll", PT_PC, ucp_Ll }, - { "Lm", PT_PC, ucp_Lm }, - { "Lo", PT_PC, ucp_Lo }, - { "Lt", PT_PC, ucp_Lt }, - { "Lu", PT_PC, ucp_Lu }, - { "M", PT_GC, ucp_M }, - { "Malayalam", PT_SC, ucp_Malayalam }, - { "Mc", PT_PC, ucp_Mc }, - { "Me", PT_PC, ucp_Me }, - { "Mn", PT_PC, ucp_Mn }, - { "Mongolian", PT_SC, ucp_Mongolian }, - { "Myanmar", PT_SC, ucp_Myanmar }, - { "N", PT_GC, ucp_N }, - { "Nd", PT_PC, ucp_Nd }, - { "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue }, - { "Nl", PT_PC, ucp_Nl }, - { "No", PT_PC, ucp_No }, - { "Ogham", PT_SC, ucp_Ogham }, - { "Old_Italic", PT_SC, ucp_Old_Italic }, - { "Old_Persian", PT_SC, ucp_Old_Persian }, - { "Oriya", PT_SC, ucp_Oriya }, - { "Osmanya", PT_SC, ucp_Osmanya }, - { "P", PT_GC, ucp_P }, - { "Pc", PT_PC, ucp_Pc }, - { "Pd", PT_PC, ucp_Pd }, - { "Pe", PT_PC, ucp_Pe }, - { "Pf", PT_PC, ucp_Pf }, - { "Pi", PT_PC, ucp_Pi }, - { "Po", PT_PC, ucp_Po }, - { "Ps", PT_PC, ucp_Ps }, - { "Runic", PT_SC, ucp_Runic }, - { "S", PT_GC, ucp_S }, - { "Sc", PT_PC, ucp_Sc }, - { "Shavian", PT_SC, ucp_Shavian }, - { "Sinhala", PT_SC, ucp_Sinhala }, - { "Sk", PT_PC, ucp_Sk }, - { "Sm", PT_PC, ucp_Sm }, - { "So", PT_PC, ucp_So }, - { "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri }, - { "Syriac", PT_SC, ucp_Syriac }, - { "Tagalog", PT_SC, ucp_Tagalog }, - { "Tagbanwa", PT_SC, ucp_Tagbanwa }, - { "Tai_Le", PT_SC, ucp_Tai_Le }, - { "Tamil", PT_SC, ucp_Tamil }, - { "Telugu", PT_SC, ucp_Telugu }, - { "Thaana", PT_SC, ucp_Thaana }, - { "Thai", PT_SC, ucp_Thai }, - { "Tibetan", PT_SC, ucp_Tibetan }, - { "Tifinagh", PT_SC, ucp_Tifinagh }, - { "Ugaritic", PT_SC, ucp_Ugaritic }, - { "Yi", PT_SC, ucp_Yi }, - { "Z", PT_GC, ucp_Z }, - { "Zl", PT_PC, ucp_Zl }, - { "Zp", PT_PC, ucp_Zp }, - { "Zs", PT_PC, ucp_Zs } + { 0, PT_ANY, 0 }, + { 4, PT_SC, ucp_Arabic }, + { 11, PT_SC, ucp_Armenian }, + { 20, PT_SC, ucp_Balinese }, + { 29, PT_SC, ucp_Bengali }, + { 37, PT_SC, ucp_Bopomofo }, + { 46, PT_SC, ucp_Braille }, + { 54, PT_SC, ucp_Buginese }, + { 63, PT_SC, ucp_Buhid }, + { 69, PT_GC, ucp_C }, + { 71, PT_SC, ucp_Canadian_Aboriginal }, + { 91, PT_SC, ucp_Carian }, + { 98, PT_PC, ucp_Cc }, + { 101, PT_PC, ucp_Cf }, + { 104, PT_SC, ucp_Cham }, + { 109, PT_SC, ucp_Cherokee }, + { 118, PT_PC, ucp_Cn }, + { 121, PT_PC, ucp_Co }, + { 124, PT_SC, ucp_Common }, + { 131, PT_SC, ucp_Coptic }, + { 138, PT_PC, ucp_Cs }, + { 141, PT_SC, ucp_Cuneiform }, + { 151, PT_SC, ucp_Cypriot }, + { 159, PT_SC, ucp_Cyrillic }, + { 168, PT_SC, ucp_Deseret }, + { 176, PT_SC, ucp_Devanagari }, + { 187, PT_SC, ucp_Ethiopic }, + { 196, PT_SC, ucp_Georgian }, + { 205, PT_SC, ucp_Glagolitic }, + { 216, PT_SC, ucp_Gothic }, + { 223, PT_SC, ucp_Greek }, + { 229, PT_SC, ucp_Gujarati }, + { 238, PT_SC, ucp_Gurmukhi }, + { 247, PT_SC, ucp_Han }, + { 251, PT_SC, ucp_Hangul }, + { 258, PT_SC, ucp_Hanunoo }, + { 266, PT_SC, ucp_Hebrew }, + { 273, PT_SC, ucp_Hiragana }, + { 282, PT_SC, ucp_Inherited }, + { 292, PT_SC, ucp_Kannada }, + { 300, PT_SC, ucp_Katakana }, + { 309, PT_SC, ucp_Kayah_Li }, + { 318, PT_SC, ucp_Kharoshthi }, + { 329, PT_SC, ucp_Khmer }, + { 335, PT_GC, ucp_L }, + { 337, PT_LAMP, 0 }, + { 340, PT_SC, ucp_Lao }, + { 344, PT_SC, ucp_Latin }, + { 350, PT_SC, ucp_Lepcha }, + { 357, PT_SC, ucp_Limbu }, + { 363, PT_SC, ucp_Linear_B }, + { 372, PT_PC, ucp_Ll }, + { 375, PT_PC, ucp_Lm }, + { 378, PT_PC, ucp_Lo }, + { 381, PT_PC, ucp_Lt }, + { 384, PT_PC, ucp_Lu }, + { 387, PT_SC, ucp_Lycian }, + { 394, PT_SC, ucp_Lydian }, + { 401, PT_GC, ucp_M }, + { 403, PT_SC, ucp_Malayalam }, + { 413, PT_PC, ucp_Mc }, + { 416, PT_PC, ucp_Me }, + { 419, PT_PC, ucp_Mn }, + { 422, PT_SC, ucp_Mongolian }, + { 432, PT_SC, ucp_Myanmar }, + { 440, PT_GC, ucp_N }, + { 442, PT_PC, ucp_Nd }, + { 445, PT_SC, ucp_New_Tai_Lue }, + { 457, PT_SC, ucp_Nko }, + { 461, PT_PC, ucp_Nl }, + { 464, PT_PC, ucp_No }, + { 467, PT_SC, ucp_Ogham }, + { 473, PT_SC, ucp_Ol_Chiki }, + { 482, PT_SC, ucp_Old_Italic }, + { 493, PT_SC, ucp_Old_Persian }, + { 505, PT_SC, ucp_Oriya }, + { 511, PT_SC, ucp_Osmanya }, + { 519, PT_GC, ucp_P }, + { 521, PT_PC, ucp_Pc }, + { 524, PT_PC, ucp_Pd }, + { 527, PT_PC, ucp_Pe }, + { 530, PT_PC, ucp_Pf }, + { 533, PT_SC, ucp_Phags_Pa }, + { 542, PT_SC, ucp_Phoenician }, + { 553, PT_PC, ucp_Pi }, + { 556, PT_PC, ucp_Po }, + { 559, PT_PC, ucp_Ps }, + { 562, PT_SC, ucp_Rejang }, + { 569, PT_SC, ucp_Runic }, + { 575, PT_GC, ucp_S }, + { 577, PT_SC, ucp_Saurashtra }, + { 588, PT_PC, ucp_Sc }, + { 591, PT_SC, ucp_Shavian }, + { 599, PT_SC, ucp_Sinhala }, + { 607, PT_PC, ucp_Sk }, + { 610, PT_PC, ucp_Sm }, + { 613, PT_PC, ucp_So }, + { 616, PT_SC, ucp_Sundanese }, + { 626, PT_SC, ucp_Syloti_Nagri }, + { 639, PT_SC, ucp_Syriac }, + { 646, PT_SC, ucp_Tagalog }, + { 654, PT_SC, ucp_Tagbanwa }, + { 663, PT_SC, ucp_Tai_Le }, + { 670, PT_SC, ucp_Tamil }, + { 676, PT_SC, ucp_Telugu }, + { 683, PT_SC, ucp_Thaana }, + { 690, PT_SC, ucp_Thai }, + { 695, PT_SC, ucp_Tibetan }, + { 703, PT_SC, ucp_Tifinagh }, + { 712, PT_SC, ucp_Ugaritic }, + { 721, PT_SC, ucp_Vai }, + { 725, PT_SC, ucp_Yi }, + { 728, PT_GC, ucp_Z }, + { 730, PT_PC, ucp_Zl }, + { 733, PT_PC, ucp_Zp }, + { 736, PT_PC, ucp_Zs } }; const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); +#endif /* SUPPORT_UTF8 */ + /* End of pcre_tables.c */ Modified: freeswitch/trunk/libs/pcre/pcre_try_flipped.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_try_flipped.c (original) +++ freeswitch/trunk/libs/pcre/pcre_try_flipped.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -43,6 +43,10 @@ auxiliary local function to flip the appropriate bytes. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -104,6 +108,7 @@ *internal_re = *re; /* To copy other fields */ internal_re->size = byteflip(re->size, sizeof(re->size)); internal_re->options = byteflip(re->options, sizeof(re->options)); +internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags)); internal_re->top_bracket = (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); internal_re->top_backref = Added: freeswitch/trunk/libs/pcre/pcre_ucd.c ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcre_ucd.c Mon Jun 8 18:51:30 2009 @@ -0,0 +1,2610 @@ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif +#include "pcre_internal.h" + +/* Unicode character database. */ +/* This file was autogenerated by the MultiStage2.py script. */ +/* Total size: 52808 bytes, block size: 128. */ +/* When recompiling tables with a new Unicode version, +please check types in the structure definition from pcre_internal.h: +typedef struct { +uschar property_0; +uschar property_1; +pcre_int32 property_2; +} ucd_record; */ + + +const ucd_record _pcre_ucd_records[] = { /* 3656 bytes, record size 8 */ + { 9, 0, 0, }, /* 0 */ + { 9, 29, 0, }, /* 1 */ + { 9, 21, 0, }, /* 2 */ + { 9, 23, 0, }, /* 3 */ + { 9, 22, 0, }, /* 4 */ + { 9, 18, 0, }, /* 5 */ + { 9, 25, 0, }, /* 6 */ + { 9, 17, 0, }, /* 7 */ + { 9, 13, 0, }, /* 8 */ + { 33, 9, 32, }, /* 9 */ + { 9, 24, 0, }, /* 10 */ + { 9, 16, 0, }, /* 11 */ + { 33, 5, -32, }, /* 12 */ + { 9, 26, 0, }, /* 13 */ + { 33, 5, 0, }, /* 14 */ + { 9, 20, 0, }, /* 15 */ + { 9, 1, 0, }, /* 16 */ + { 9, 15, 0, }, /* 17 */ + { 9, 5, 743, }, /* 18 */ + { 9, 19, 0, }, /* 19 */ + { 33, 5, 121, }, /* 20 */ + { 33, 9, 1, }, /* 21 */ + { 33, 5, -1, }, /* 22 */ + { 33, 9, -199, }, /* 23 */ + { 33, 5, -232, }, /* 24 */ + { 33, 9, -121, }, /* 25 */ + { 33, 5, -300, }, /* 26 */ + { 33, 5, 195, }, /* 27 */ + { 33, 9, 210, }, /* 28 */ + { 33, 9, 206, }, /* 29 */ + { 33, 9, 205, }, /* 30 */ + { 33, 9, 79, }, /* 31 */ + { 33, 9, 202, }, /* 32 */ + { 33, 9, 203, }, /* 33 */ + { 33, 9, 207, }, /* 34 */ + { 33, 5, 97, }, /* 35 */ + { 33, 9, 211, }, /* 36 */ + { 33, 9, 209, }, /* 37 */ + { 33, 5, 163, }, /* 38 */ + { 33, 9, 213, }, /* 39 */ + { 33, 5, 130, }, /* 40 */ + { 33, 9, 214, }, /* 41 */ + { 33, 9, 218, }, /* 42 */ + { 33, 9, 217, }, /* 43 */ + { 33, 9, 219, }, /* 44 */ + { 33, 7, 0, }, /* 45 */ + { 33, 5, 56, }, /* 46 */ + { 33, 9, 2, }, /* 47 */ + { 33, 8, -1, }, /* 48 */ + { 33, 5, -2, }, /* 49 */ + { 33, 5, -79, }, /* 50 */ + { 33, 9, -97, }, /* 51 */ + { 33, 9, -56, }, /* 52 */ + { 33, 9, -130, }, /* 53 */ + { 33, 9, 10795, }, /* 54 */ + { 33, 9, -163, }, /* 55 */ + { 33, 9, 10792, }, /* 56 */ + { 33, 9, -195, }, /* 57 */ + { 33, 9, 69, }, /* 58 */ + { 33, 9, 71, }, /* 59 */ + { 33, 5, 10783, }, /* 60 */ + { 33, 5, 10780, }, /* 61 */ + { 33, 5, -210, }, /* 62 */ + { 33, 5, -206, }, /* 63 */ + { 33, 5, -205, }, /* 64 */ + { 33, 5, -202, }, /* 65 */ + { 33, 5, -203, }, /* 66 */ + { 33, 5, -207, }, /* 67 */ + { 33, 5, -209, }, /* 68 */ + { 33, 5, -211, }, /* 69 */ + { 33, 5, 10743, }, /* 70 */ + { 33, 5, 10749, }, /* 71 */ + { 33, 5, -213, }, /* 72 */ + { 33, 5, -214, }, /* 73 */ + { 33, 5, 10727, }, /* 74 */ + { 33, 5, -218, }, /* 75 */ + { 33, 5, -69, }, /* 76 */ + { 33, 5, -217, }, /* 77 */ + { 33, 5, -71, }, /* 78 */ + { 33, 5, -219, }, /* 79 */ + { 33, 6, 0, }, /* 80 */ + { 9, 6, 0, }, /* 81 */ + { 27, 12, 0, }, /* 82 */ + { 27, 12, 84, }, /* 83 */ + { 19, 9, 1, }, /* 84 */ + { 19, 5, -1, }, /* 85 */ + { 19, 24, 0, }, /* 86 */ + { 9, 2, 0, }, /* 87 */ + { 19, 6, 0, }, /* 88 */ + { 19, 5, 130, }, /* 89 */ + { 19, 9, 38, }, /* 90 */ + { 19, 9, 37, }, /* 91 */ + { 19, 9, 64, }, /* 92 */ + { 19, 9, 63, }, /* 93 */ + { 19, 5, 0, }, /* 94 */ + { 19, 9, 32, }, /* 95 */ + { 19, 5, -38, }, /* 96 */ + { 19, 5, -37, }, /* 97 */ + { 19, 5, -32, }, /* 98 */ + { 19, 5, -31, }, /* 99 */ + { 19, 5, -64, }, /* 100 */ + { 19, 5, -63, }, /* 101 */ + { 19, 9, 8, }, /* 102 */ + { 19, 5, -62, }, /* 103 */ + { 19, 5, -57, }, /* 104 */ + { 19, 9, 0, }, /* 105 */ + { 19, 5, -47, }, /* 106 */ + { 19, 5, -54, }, /* 107 */ + { 19, 5, -8, }, /* 108 */ + { 10, 9, 1, }, /* 109 */ + { 10, 5, -1, }, /* 110 */ + { 19, 5, -86, }, /* 111 */ + { 19, 5, -80, }, /* 112 */ + { 19, 5, 7, }, /* 113 */ + { 19, 9, -60, }, /* 114 */ + { 19, 5, -96, }, /* 115 */ + { 19, 25, 0, }, /* 116 */ + { 19, 9, -7, }, /* 117 */ + { 19, 9, -130, }, /* 118 */ + { 12, 9, 80, }, /* 119 */ + { 12, 9, 32, }, /* 120 */ + { 12, 5, -32, }, /* 121 */ + { 12, 5, -80, }, /* 122 */ + { 12, 9, 1, }, /* 123 */ + { 12, 5, -1, }, /* 124 */ + { 12, 26, 0, }, /* 125 */ + { 12, 12, 0, }, /* 126 */ + { 12, 11, 0, }, /* 127 */ + { 12, 9, 15, }, /* 128 */ + { 12, 5, -15, }, /* 129 */ + { 1, 9, 48, }, /* 130 */ + { 1, 6, 0, }, /* 131 */ + { 1, 21, 0, }, /* 132 */ + { 1, 5, -48, }, /* 133 */ + { 1, 5, 0, }, /* 134 */ + { 1, 17, 0, }, /* 135 */ + { 25, 12, 0, }, /* 136 */ + { 25, 17, 0, }, /* 137 */ + { 25, 21, 0, }, /* 138 */ + { 25, 7, 0, }, /* 139 */ + { 0, 25, 0, }, /* 140 */ + { 0, 21, 0, }, /* 141 */ + { 0, 23, 0, }, /* 142 */ + { 0, 26, 0, }, /* 143 */ + { 0, 12, 0, }, /* 144 */ + { 0, 7, 0, }, /* 145 */ + { 0, 11, 0, }, /* 146 */ + { 0, 6, 0, }, /* 147 */ + { 0, 13, 0, }, /* 148 */ + { 49, 21, 0, }, /* 149 */ + { 49, 1, 0, }, /* 150 */ + { 49, 7, 0, }, /* 151 */ + { 49, 12, 0, }, /* 152 */ + { 55, 7, 0, }, /* 153 */ + { 55, 12, 0, }, /* 154 */ + { 63, 13, 0, }, /* 155 */ + { 63, 7, 0, }, /* 156 */ + { 63, 12, 0, }, /* 157 */ + { 63, 6, 0, }, /* 158 */ + { 63, 26, 0, }, /* 159 */ + { 63, 21, 0, }, /* 160 */ + { 14, 12, 0, }, /* 161 */ + { 14, 10, 0, }, /* 162 */ + { 14, 7, 0, }, /* 163 */ + { 14, 13, 0, }, /* 164 */ + { 14, 6, 0, }, /* 165 */ + { 2, 12, 0, }, /* 166 */ + { 2, 10, 0, }, /* 167 */ + { 2, 7, 0, }, /* 168 */ + { 2, 13, 0, }, /* 169 */ + { 2, 23, 0, }, /* 170 */ + { 2, 15, 0, }, /* 171 */ + { 2, 26, 0, }, /* 172 */ + { 21, 12, 0, }, /* 173 */ + { 21, 10, 0, }, /* 174 */ + { 21, 7, 0, }, /* 175 */ + { 21, 13, 0, }, /* 176 */ + { 20, 12, 0, }, /* 177 */ + { 20, 10, 0, }, /* 178 */ + { 20, 7, 0, }, /* 179 */ + { 20, 13, 0, }, /* 180 */ + { 20, 23, 0, }, /* 181 */ + { 43, 12, 0, }, /* 182 */ + { 43, 10, 0, }, /* 183 */ + { 43, 7, 0, }, /* 184 */ + { 43, 13, 0, }, /* 185 */ + { 43, 26, 0, }, /* 186 */ + { 53, 12, 0, }, /* 187 */ + { 53, 7, 0, }, /* 188 */ + { 53, 10, 0, }, /* 189 */ + { 53, 13, 0, }, /* 190 */ + { 53, 15, 0, }, /* 191 */ + { 53, 26, 0, }, /* 192 */ + { 53, 23, 0, }, /* 193 */ + { 54, 10, 0, }, /* 194 */ + { 54, 7, 0, }, /* 195 */ + { 54, 12, 0, }, /* 196 */ + { 54, 13, 0, }, /* 197 */ + { 54, 15, 0, }, /* 198 */ + { 54, 26, 0, }, /* 199 */ + { 28, 10, 0, }, /* 200 */ + { 28, 7, 0, }, /* 201 */ + { 28, 12, 0, }, /* 202 */ + { 28, 13, 0, }, /* 203 */ + { 36, 10, 0, }, /* 204 */ + { 36, 7, 0, }, /* 205 */ + { 36, 12, 0, }, /* 206 */ + { 36, 13, 0, }, /* 207 */ + { 36, 15, 0, }, /* 208 */ + { 36, 26, 0, }, /* 209 */ + { 47, 10, 0, }, /* 210 */ + { 47, 7, 0, }, /* 211 */ + { 47, 12, 0, }, /* 212 */ + { 47, 21, 0, }, /* 213 */ + { 56, 7, 0, }, /* 214 */ + { 56, 12, 0, }, /* 215 */ + { 56, 6, 0, }, /* 216 */ + { 56, 21, 0, }, /* 217 */ + { 56, 13, 0, }, /* 218 */ + { 32, 7, 0, }, /* 219 */ + { 32, 12, 0, }, /* 220 */ + { 32, 6, 0, }, /* 221 */ + { 32, 13, 0, }, /* 222 */ + { 57, 7, 0, }, /* 223 */ + { 57, 26, 0, }, /* 224 */ + { 57, 21, 0, }, /* 225 */ + { 57, 12, 0, }, /* 226 */ + { 57, 13, 0, }, /* 227 */ + { 57, 15, 0, }, /* 228 */ + { 57, 22, 0, }, /* 229 */ + { 57, 18, 0, }, /* 230 */ + { 57, 10, 0, }, /* 231 */ + { 38, 7, 0, }, /* 232 */ + { 38, 10, 0, }, /* 233 */ + { 38, 12, 0, }, /* 234 */ + { 38, 13, 0, }, /* 235 */ + { 38, 21, 0, }, /* 236 */ + { 38, 26, 0, }, /* 237 */ + { 16, 9, 7264, }, /* 238 */ + { 16, 7, 0, }, /* 239 */ + { 16, 6, 0, }, /* 240 */ + { 23, 7, 0, }, /* 241 */ + { 15, 7, 0, }, /* 242 */ + { 15, 12, 0, }, /* 243 */ + { 15, 26, 0, }, /* 244 */ + { 15, 21, 0, }, /* 245 */ + { 15, 15, 0, }, /* 246 */ + { 8, 7, 0, }, /* 247 */ + { 7, 7, 0, }, /* 248 */ + { 7, 21, 0, }, /* 249 */ + { 40, 29, 0, }, /* 250 */ + { 40, 7, 0, }, /* 251 */ + { 40, 22, 0, }, /* 252 */ + { 40, 18, 0, }, /* 253 */ + { 45, 7, 0, }, /* 254 */ + { 45, 14, 0, }, /* 255 */ + { 50, 7, 0, }, /* 256 */ + { 50, 12, 0, }, /* 257 */ + { 24, 7, 0, }, /* 258 */ + { 24, 12, 0, }, /* 259 */ + { 6, 7, 0, }, /* 260 */ + { 6, 12, 0, }, /* 261 */ + { 51, 7, 0, }, /* 262 */ + { 51, 12, 0, }, /* 263 */ + { 31, 7, 0, }, /* 264 */ + { 31, 1, 0, }, /* 265 */ + { 31, 10, 0, }, /* 266 */ + { 31, 12, 0, }, /* 267 */ + { 31, 21, 0, }, /* 268 */ + { 31, 6, 0, }, /* 269 */ + { 31, 23, 0, }, /* 270 */ + { 31, 13, 0, }, /* 271 */ + { 31, 15, 0, }, /* 272 */ + { 37, 21, 0, }, /* 273 */ + { 37, 17, 0, }, /* 274 */ + { 37, 12, 0, }, /* 275 */ + { 37, 29, 0, }, /* 276 */ + { 37, 13, 0, }, /* 277 */ + { 37, 7, 0, }, /* 278 */ + { 37, 6, 0, }, /* 279 */ + { 34, 7, 0, }, /* 280 */ + { 34, 12, 0, }, /* 281 */ + { 34, 10, 0, }, /* 282 */ + { 34, 26, 0, }, /* 283 */ + { 34, 21, 0, }, /* 284 */ + { 34, 13, 0, }, /* 285 */ + { 52, 7, 0, }, /* 286 */ + { 39, 7, 0, }, /* 287 */ + { 39, 10, 0, }, /* 288 */ + { 39, 13, 0, }, /* 289 */ + { 39, 21, 0, }, /* 290 */ + { 31, 26, 0, }, /* 291 */ + { 5, 7, 0, }, /* 292 */ + { 5, 12, 0, }, /* 293 */ + { 5, 10, 0, }, /* 294 */ + { 5, 21, 0, }, /* 295 */ + { 61, 12, 0, }, /* 296 */ + { 61, 10, 0, }, /* 297 */ + { 61, 7, 0, }, /* 298 */ + { 61, 13, 0, }, /* 299 */ + { 61, 21, 0, }, /* 300 */ + { 61, 26, 0, }, /* 301 */ + { 75, 12, 0, }, /* 302 */ + { 75, 10, 0, }, /* 303 */ + { 75, 7, 0, }, /* 304 */ + { 75, 13, 0, }, /* 305 */ + { 69, 7, 0, }, /* 306 */ + { 69, 10, 0, }, /* 307 */ + { 69, 12, 0, }, /* 308 */ + { 69, 21, 0, }, /* 309 */ + { 69, 13, 0, }, /* 310 */ + { 72, 13, 0, }, /* 311 */ + { 72, 7, 0, }, /* 312 */ + { 72, 6, 0, }, /* 313 */ + { 72, 21, 0, }, /* 314 */ + { 12, 5, 0, }, /* 315 */ + { 12, 6, 0, }, /* 316 */ + { 33, 5, 35332, }, /* 317 */ + { 33, 5, 3814, }, /* 318 */ + { 33, 5, -59, }, /* 319 */ + { 33, 9, -7615, }, /* 320 */ + { 19, 5, 8, }, /* 321 */ + { 19, 9, -8, }, /* 322 */ + { 19, 5, 74, }, /* 323 */ + { 19, 5, 86, }, /* 324 */ + { 19, 5, 100, }, /* 325 */ + { 19, 5, 128, }, /* 326 */ + { 19, 5, 112, }, /* 327 */ + { 19, 5, 126, }, /* 328 */ + { 19, 8, -8, }, /* 329 */ + { 19, 5, 9, }, /* 330 */ + { 19, 9, -74, }, /* 331 */ + { 19, 8, -9, }, /* 332 */ + { 19, 5, -7205, }, /* 333 */ + { 19, 9, -86, }, /* 334 */ + { 19, 9, -100, }, /* 335 */ + { 19, 9, -112, }, /* 336 */ + { 19, 9, -128, }, /* 337 */ + { 19, 9, -126, }, /* 338 */ + { 27, 1, 0, }, /* 339 */ + { 9, 27, 0, }, /* 340 */ + { 9, 28, 0, }, /* 341 */ + { 27, 11, 0, }, /* 342 */ + { 9, 9, 0, }, /* 343 */ + { 9, 5, 0, }, /* 344 */ + { 19, 9, -7517, }, /* 345 */ + { 33, 9, -8383, }, /* 346 */ + { 33, 9, -8262, }, /* 347 */ + { 33, 9, 28, }, /* 348 */ + { 9, 7, 0, }, /* 349 */ + { 33, 5, -28, }, /* 350 */ + { 33, 14, 16, }, /* 351 */ + { 33, 14, -16, }, /* 352 */ + { 33, 14, 0, }, /* 353 */ + { 9, 26, 26, }, /* 354 */ + { 9, 26, -26, }, /* 355 */ + { 4, 26, 0, }, /* 356 */ + { 17, 9, 48, }, /* 357 */ + { 17, 5, -48, }, /* 358 */ + { 33, 9, -10743, }, /* 359 */ + { 33, 9, -3814, }, /* 360 */ + { 33, 9, -10727, }, /* 361 */ + { 33, 5, -10795, }, /* 362 */ + { 33, 5, -10792, }, /* 363 */ + { 33, 9, -10780, }, /* 364 */ + { 33, 9, -10749, }, /* 365 */ + { 33, 9, -10783, }, /* 366 */ + { 10, 5, 0, }, /* 367 */ + { 10, 26, 0, }, /* 368 */ + { 10, 21, 0, }, /* 369 */ + { 10, 15, 0, }, /* 370 */ + { 16, 5, -7264, }, /* 371 */ + { 58, 7, 0, }, /* 372 */ + { 58, 6, 0, }, /* 373 */ + { 22, 26, 0, }, /* 374 */ + { 22, 6, 0, }, /* 375 */ + { 22, 14, 0, }, /* 376 */ + { 26, 7, 0, }, /* 377 */ + { 26, 6, 0, }, /* 378 */ + { 29, 7, 0, }, /* 379 */ + { 29, 6, 0, }, /* 380 */ + { 3, 7, 0, }, /* 381 */ + { 23, 26, 0, }, /* 382 */ + { 29, 26, 0, }, /* 383 */ + { 22, 7, 0, }, /* 384 */ + { 60, 7, 0, }, /* 385 */ + { 60, 6, 0, }, /* 386 */ + { 60, 26, 0, }, /* 387 */ + { 76, 7, 0, }, /* 388 */ + { 76, 6, 0, }, /* 389 */ + { 76, 21, 0, }, /* 390 */ + { 76, 13, 0, }, /* 391 */ + { 12, 7, 0, }, /* 392 */ + { 12, 21, 0, }, /* 393 */ + { 33, 9, -35332, }, /* 394 */ + { 48, 7, 0, }, /* 395 */ + { 48, 12, 0, }, /* 396 */ + { 48, 10, 0, }, /* 397 */ + { 48, 26, 0, }, /* 398 */ + { 64, 7, 0, }, /* 399 */ + { 64, 21, 0, }, /* 400 */ + { 74, 10, 0, }, /* 401 */ + { 74, 7, 0, }, /* 402 */ + { 74, 12, 0, }, /* 403 */ + { 74, 21, 0, }, /* 404 */ + { 74, 13, 0, }, /* 405 */ + { 68, 13, 0, }, /* 406 */ + { 68, 7, 0, }, /* 407 */ + { 68, 12, 0, }, /* 408 */ + { 68, 21, 0, }, /* 409 */ + { 73, 7, 0, }, /* 410 */ + { 73, 12, 0, }, /* 411 */ + { 73, 10, 0, }, /* 412 */ + { 73, 21, 0, }, /* 413 */ + { 67, 7, 0, }, /* 414 */ + { 67, 12, 0, }, /* 415 */ + { 67, 10, 0, }, /* 416 */ + { 67, 13, 0, }, /* 417 */ + { 67, 21, 0, }, /* 418 */ + { 9, 4, 0, }, /* 419 */ + { 9, 3, 0, }, /* 420 */ + { 25, 25, 0, }, /* 421 */ + { 35, 7, 0, }, /* 422 */ + { 19, 14, 0, }, /* 423 */ + { 19, 15, 0, }, /* 424 */ + { 19, 26, 0, }, /* 425 */ + { 70, 7, 0, }, /* 426 */ + { 66, 7, 0, }, /* 427 */ + { 41, 7, 0, }, /* 428 */ + { 41, 15, 0, }, /* 429 */ + { 18, 7, 0, }, /* 430 */ + { 18, 14, 0, }, /* 431 */ + { 59, 7, 0, }, /* 432 */ + { 59, 21, 0, }, /* 433 */ + { 42, 7, 0, }, /* 434 */ + { 42, 21, 0, }, /* 435 */ + { 42, 14, 0, }, /* 436 */ + { 13, 9, 40, }, /* 437 */ + { 13, 5, -40, }, /* 438 */ + { 46, 7, 0, }, /* 439 */ + { 44, 7, 0, }, /* 440 */ + { 44, 13, 0, }, /* 441 */ + { 11, 7, 0, }, /* 442 */ + { 65, 7, 0, }, /* 443 */ + { 65, 15, 0, }, /* 444 */ + { 65, 21, 0, }, /* 445 */ + { 71, 7, 0, }, /* 446 */ + { 71, 21, 0, }, /* 447 */ + { 30, 7, 0, }, /* 448 */ + { 30, 12, 0, }, /* 449 */ + { 30, 15, 0, }, /* 450 */ + { 30, 21, 0, }, /* 451 */ + { 62, 7, 0, }, /* 452 */ + { 62, 14, 0, }, /* 453 */ + { 62, 21, 0, }, /* 454 */ + { 9, 10, 0, }, /* 455 */ + { 19, 12, 0, }, /* 456 */ +}; + +const uschar _pcre_ucd_stage1[] = { /* 8704 bytes */ + 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, /* U+0000 */ + 16, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, /* U+0800 */ + 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 40, 40, 41, 42, 43, 44, /* U+1000 */ + 45, 46, 47, 48, 49, 16, 50, 51, 52, 16, 53, 54, 55, 56, 57, 58, /* U+1800 */ + 59, 60, 61, 62, 63, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, /* U+2000 */ + 74, 74, 63, 75, 63, 63, 76, 16, 77, 78, 79, 80, 81, 82, 83, 84, /* U+2800 */ + 85, 86, 87, 88, 89, 90, 91, 68, 92, 92, 92, 92, 92, 92, 92, 92, /* U+3000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+3800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+4000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 93, 92, 92, 92, 92, /* U+4800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+5000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+5800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+6000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+6800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+7000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+7800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+8000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+8800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+9000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 94, /* U+9800 */ + 95, 96, 96, 96, 96, 96, 96, 96, 96, 97, 98, 98, 99,100,101,102, /* U+A000 */ +103,104,105, 16,106, 16, 16, 16,107,107,107,107,107,107,107,107, /* U+A800 */ +107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+B000 */ +107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+B800 */ +107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+C000 */ +107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+C800 */ +107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,108, /* U+D000 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, /* U+D800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+E000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+E800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F000 */ +110,110, 92, 92,111,112,113,114,115,115,116,117,118,119,120,121, /* U+F800 */ +122,123,124,125, 16,126,127,128,129,130, 16, 16, 16, 16, 16, 16, /* U+10000 */ +131, 16,132, 16,133, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+10800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+11000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+11800 */ +134,134,134,134,134,134,135, 16,136, 16, 16, 16, 16, 16, 16, 16, /* U+12000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+12800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+13000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+13800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+14000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+14800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+15000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+15800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+16000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+16800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+17000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+17800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+18000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+18800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+19000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+19800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1C800 */ + 68,137,138,139,140, 16,141, 16,142,143,144,145,146,147,148,149, /* U+1D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1E800 */ +150,151, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1F800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+20000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+20800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+21000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+21800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+22000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+22800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+23000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+23800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+24000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+24800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+25000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+25800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+26000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+26800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+27000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+27800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+28000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+28800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+29000 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+29800 */ + 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,152, 16, 16, /* U+2A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2F000 */ + 92, 92, 92, 92,153, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+30000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+30800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+31000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+31800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+32000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+32800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+33000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+33800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+34000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+34800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+35000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+35800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+36000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+36800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+37000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+37800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+38000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+38800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+39000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+39800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+40000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+40800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+41000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+41800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+42000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+42800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+43000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+43800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+44000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+44800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+45000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+45800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+46000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+46800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+47000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+47800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+48000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+48800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+49000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+49800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+50000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+50800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+51000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+51800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+52000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+52800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+53000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+53800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+54000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+54800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+55000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+55800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+56000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+56800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+57000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+57800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+58000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+58800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+59000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+59800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+60000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+60800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+61000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+61800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+62000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+62800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+63000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+63800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+64000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+64800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+65000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+65800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+66000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+66800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+67000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+67800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+68000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+68800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+69000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+69800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+70000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+70800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+71000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+71800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+72000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+72800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+73000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+73800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+74000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+74800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+75000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+75800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+76000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+76800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+77000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+77800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+78000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+78800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+79000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+79800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+80000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+80800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+81000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+81800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+82000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+82800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+83000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+83800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+84000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+84800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+85000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+85800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+86000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+86800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+87000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+87800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+88000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+88800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+89000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+89800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+90000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+90800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+91000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+91800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+92000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+92800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+93000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+93800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+94000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+94800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+95000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+95800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+96000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+96800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+97000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+97800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+98000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+98800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+99000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+99800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9A000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9A800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9B000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9B800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9C000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9C800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9D000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9D800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9E000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9E800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9F000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9F800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A0000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A0800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A1000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A1800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A2000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A2800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A3000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A3800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A4000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A4800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A5000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A5800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A6000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A6800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A7000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A7800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A8000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A8800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A9000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A9800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AA000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AA800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AB000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AB800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AC000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AC800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AD000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AD800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AE000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AE800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AF000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AF800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B0000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B0800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B1000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B1800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B2000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B2800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B3000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B3800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B4000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B4800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B5000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B5800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B6000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B6800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B7000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B7800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B8000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B8800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B9000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B9800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BA000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BA800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BB000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BB800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BC000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BC800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BD000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BD800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BE000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BE800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BF000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BF800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C0000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C0800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C1000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C1800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C2000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C2800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C3000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C3800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C4000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C4800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C5000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C5800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C6000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C6800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C7000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C7800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C8000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C8800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C9000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C9800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CA000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CA800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CB000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CB800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CC000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CC800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CD000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CD800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CE000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CE800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CF000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CF800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D0000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D0800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D1000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D1800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D2000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D2800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D3000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D3800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D4000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D4800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D5000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D5800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D6000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D6800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D7000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D7800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D8000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D8800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D9000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D9800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DA000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DA800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DB000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DB800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DC000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DC800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DD000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DD800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DE000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DE800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DF000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DF800 */ +154, 16,155,156, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E0000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E0800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E1000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E1800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E2000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E2800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E3000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E3800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E4000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E4800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E5000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E5800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E6000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E6800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E7000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E7800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E8000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E8800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E9000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E9800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EA000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EA800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EB000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EB800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EC000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EC800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+ED000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+ED800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EE000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EE800 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EF000 */ + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EF800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F0000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F0800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F1000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F1800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F2000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F2800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F3000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F3800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F4000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F4800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F5000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F5800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F6000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F6800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F7000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F7800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F8000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F8800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F9000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F9800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FA000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FA800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FB000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FB800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FC000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FC800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FD000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FD800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FE000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FE800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FF000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,157, /* U+FF800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+100000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+100800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+101000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+101800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+102000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+102800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+103000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+103800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+104000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+104800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+105000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+105800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+106000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+106800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+107000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+107800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+108000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+108800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+109000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+109800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10A000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10A800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10B000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10B800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10C000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10C800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10D000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10D800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10E000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10E800 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10F000 */ +110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,157, /* U+10F800 */ +}; + +const pcre_uint16 _pcre_ucd_stage2[] = { /* 40448 bytes, block = 128 */ +/* block 0 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 1, 2, 2, 2, 3, 2, 2, 2, 4, 5, 2, 6, 2, 7, 2, 2, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 2, 2, 6, 6, 6, 2, + 2, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 2, 5, 10, 11, + 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, + 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 4, 6, 5, 6, 0, + +/* block 1 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 1, 2, 3, 3, 3, 3, 13, 13, 10, 13, 14, 15, 6, 16, 13, 10, + 13, 6, 17, 17, 10, 18, 13, 2, 10, 17, 14, 19, 17, 17, 17, 2, + 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + 9, 9, 9, 9, 9, 9, 9, 6, 9, 9, 9, 9, 9, 9, 9, 14, + 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, + 12, 12, 12, 12, 12, 12, 12, 6, 12, 12, 12, 12, 12, 12, 12, 20, + +/* block 2 */ + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 23, 24, 21, 22, 21, 22, 21, 22, 14, 21, 22, 21, 22, 21, 22, 21, + 22, 21, 22, 21, 22, 21, 22, 21, 22, 14, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 25, 21, 22, 21, 22, 21, 22, 26, + +/* block 3 */ + 27, 28, 21, 22, 21, 22, 29, 21, 22, 30, 30, 21, 22, 14, 31, 32, + 33, 21, 22, 30, 34, 35, 36, 37, 21, 22, 38, 14, 36, 39, 40, 41, + 21, 22, 21, 22, 21, 22, 42, 21, 22, 42, 14, 14, 21, 22, 42, 21, + 22, 43, 43, 21, 22, 21, 22, 44, 21, 22, 14, 45, 21, 22, 14, 46, + 45, 45, 45, 45, 47, 48, 49, 47, 48, 49, 47, 48, 49, 21, 22, 21, + 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 50, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 14, 47, 48, 49, 21, 22, 51, 52, 21, 22, 21, 22, 21, 22, 21, 22, + +/* block 4 */ + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 53, 14, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 14, 14, 14, 14, 14, 14, 54, 21, 22, 55, 56, 14, + 14, 21, 22, 57, 58, 59, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 60, 61, 14, 62, 63, 14, 64, 64, 14, 65, 14, 66, 14, 14, 14, 14, + 64, 14, 14, 67, 14, 14, 14, 14, 68, 69, 14, 70, 14, 14, 14, 69, + 14, 71, 72, 14, 14, 73, 14, 14, 14, 14, 14, 14, 14, 74, 14, 14, + +/* block 5 */ + 75, 14, 14, 75, 14, 14, 14, 14, 75, 76, 77, 77, 78, 14, 14, 14, + 14, 14, 79, 14, 45, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 81, 81, 81, 81, 81, 81, 81, + 81, 81, 10, 10, 10, 10, 81, 81, 81, 81, 81, 81, 81, 81, 81, 81, + 81, 81, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + 80, 80, 80, 80, 80, 10, 10, 10, 10, 10, 10, 10, 81, 10, 81, 10, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + +/* block 6 */ + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 83, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 84, 85, 84, 85, 81, 86, 84, 85, 87, 87, 88, 89, 89, 89, 2, 87, + +/* block 7 */ + 87, 87, 87, 87, 86, 10, 90, 2, 91, 91, 91, 87, 92, 87, 93, 93, + 94, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, + 95, 95, 87, 95, 95, 95, 95, 95, 95, 95, 95, 95, 96, 97, 97, 97, + 94, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, + 98, 98, 99, 98, 98, 98, 98, 98, 98, 98, 98, 98,100,101,101,102, +103,104,105,105,105,106,107,108, 84, 85, 84, 85, 84, 85, 84, 85, + 84, 85,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +111,112,113, 94,114,115,116, 84, 85,117, 84, 85, 94,118,118,118, + +/* block 8 */ +119,119,119,119,119,119,119,119,119,119,119,119,119,119,119,119, +120,120,120,120,120,120,120,120,120,120,120,120,120,120,120,120, +120,120,120,120,120,120,120,120,120,120,120,120,120,120,120,120, +121,121,121,121,121,121,121,121,121,121,121,121,121,121,121,121, +121,121,121,121,121,121,121,121,121,121,121,121,121,121,121,121, +122,122,122,122,122,122,122,122,122,122,122,122,122,122,122,122, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, + +/* block 9 */ +123,124,125,126,126,126,126,126,127,127,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +128,123,124,123,124,123,124,123,124,123,124,123,124,123,124,129, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, + +/* block 10 */ +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87,130,130,130,130,130,130,130,130,130,130,130,130,130,130,130, +130,130,130,130,130,130,130,130,130,130,130,130,130,130,130,130, +130,130,130,130,130,130,130, 87, 87,131,132,132,132,132,132,132, + 87,133,133,133,133,133,133,133,133,133,133,133,133,133,133,133, +133,133,133,133,133,133,133,133,133,133,133,133,133,133,133,133, + +/* block 11 */ +133,133,133,133,133,133,133,134, 87, 2,135, 87, 87, 87, 87, 87, + 87,136,136,136,136,136,136,136,136,136,136,136,136,136,136,136, +136,136,136,136,136,136,136,136,136,136,136,136,136,136,136,136, +136,136,136,136,136,136,136,136,136,136,136,136,136,136,137,136, +138,136,136,138,136,136,138,136, 87, 87, 87, 87, 87, 87, 87, 87, +139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, +139,139,139,139,139,139,139,139,139,139,139, 87, 87, 87, 87, 87, +139,139,139,138,138, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 12 */ + 16, 16, 16, 16, 87, 87,140,140,140,141,141,142, 2,141,143,143, +144,144,144,144,144,144,144,144,144,144,144, 2, 87, 87,141, 2, + 87,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + 81,145,145,145,145,145,145,145,145,145,145, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82,144,144,144,144,144,144,144,144,144, 87, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,141,141,141,141,145,145, + 82,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 13 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,141,145,144,144,144,144,144,144,144, 16,146,144, +144,144,144,144,144,147,147,144,144,143,144,144,144,144,145,145, +148,148,148,148,148,148,148,148,148,148,145,145,145,143,143,145, + +/* block 14 */ +149,149,149,149,149,149,149,149,149,149,149,149,149,149, 87,150, +151,152,151,151,151,151,151,151,151,151,151,151,151,151,151,151, +151,151,151,151,151,151,151,151,151,151,151,151,151,151,151,151, +152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152, +152,152,152,152,152,152,152,152,152,152,152, 87, 87,151,151,151, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 15 */ +153,153,153,153,153,153,153,153,153,153,153,153,153,153,153,153, +153,153,153,153,153,153,153,153,153,153,153,153,153,153,153,153, +153,153,153,153,153,153,154,154,154,154,154,154,154,154,154,154, +154,153, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +155,155,155,155,155,155,155,155,155,155,156,156,156,156,156,156, +156,156,156,156,156,156,156,156,156,156,156,156,156,156,156,156, +156,156,156,156,156,156,156,156,156,156,156,157,157,157,157,157, +157,157,157,157,158,158,159,160,160,160,158, 87, 87, 87, 87, 87, + +/* block 16 */ + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 17 */ + 87,161,161,162,163,163,163,163,163,163,163,163,163,163,163,163, +163,163,163,163,163,163,163,163,163,163,163,163,163,163,163,163, +163,163,163,163,163,163,163,163,163,163,163,163,163,163,163,163, +163,163,163,163,163,163,163,163,163,163, 87, 87,161,163,162,162, +162,161,161,161,161,161,161,161,161,162,162,162,162,161, 87, 87, +163, 82, 82,161,161, 87, 87, 87,163,163,163,163,163,163,163,163, +163,163,161,161, 2, 2,164,164,164,164,164,164,164,164,164,164, + 2,165,163, 87, 87, 87, 87, 87, 87, 87, 87,163,163,163,163,163, + +/* block 18 */ + 87,166,167,167, 87,168,168,168,168,168,168,168,168, 87, 87,168, +168, 87, 87,168,168,168,168,168,168,168,168,168,168,168,168,168, +168,168,168,168,168,168,168,168,168, 87,168,168,168,168,168,168, +168, 87,168, 87, 87, 87,168,168,168,168, 87, 87,166,168,167,167, +167,166,166,166,166, 87, 87,167,167, 87, 87,167,167,166,168, 87, + 87, 87, 87, 87, 87, 87, 87,167, 87, 87, 87, 87,168,168, 87,168, +168,168,166,166, 87, 87,169,169,169,169,169,169,169,169,169,169, +168,168,170,170,171,171,171,171,171,171,172, 87, 87, 87, 87, 87, + +/* block 19 */ + 87,173,173,174, 87,175,175,175,175,175,175, 87, 87, 87, 87,175, +175, 87, 87,175,175,175,175,175,175,175,175,175,175,175,175,175, +175,175,175,175,175,175,175,175,175, 87,175,175,175,175,175,175, +175, 87,175,175, 87,175,175, 87,175,175, 87, 87,173, 87,174,174, +174,173,173, 87, 87, 87, 87,173,173, 87, 87,173,173,173, 87, 87, + 87,173, 87, 87, 87, 87, 87, 87, 87,175,175,175,175, 87,175, 87, + 87, 87, 87, 87, 87, 87,176,176,176,176,176,176,176,176,176,176, +173,173,175,175,175,173, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 20 */ + 87,177,177,178, 87,179,179,179,179,179,179,179,179,179, 87,179, +179,179, 87,179,179,179,179,179,179,179,179,179,179,179,179,179, +179,179,179,179,179,179,179,179,179, 87,179,179,179,179,179,179, +179, 87,179,179, 87,179,179,179,179,179, 87, 87,177,179,178,178, +178,177,177,177,177,177, 87,177,177,178, 87,178,178,177, 87, 87, +179, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +179,179,177,177, 87, 87,180,180,180,180,180,180,180,180,180,180, + 87,181, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 21 */ + 87,182,183,183, 87,184,184,184,184,184,184,184,184, 87, 87,184, +184, 87, 87,184,184,184,184,184,184,184,184,184,184,184,184,184, +184,184,184,184,184,184,184,184,184, 87,184,184,184,184,184,184, +184, 87,184,184, 87,184,184,184,184,184, 87, 87,182,184,183,182, +183,182,182,182,182, 87, 87,183,183, 87, 87,183,183,182, 87, 87, + 87, 87, 87, 87, 87, 87,182,183, 87, 87, 87, 87,184,184, 87,184, +184,184,182,182, 87, 87,185,185,185,185,185,185,185,185,185,185, +186,184, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 22 */ + 87, 87,187,188, 87,188,188,188,188,188,188, 87, 87, 87,188,188, +188, 87,188,188,188,188, 87, 87, 87,188,188, 87,188, 87,188,188, + 87, 87, 87,188,188, 87, 87, 87,188,188,188, 87, 87, 87,188,188, +188,188,188,188,188,188,188,188,188,188, 87, 87, 87, 87,189,189, +187,189,189, 87, 87, 87,189,189,189, 87,189,189,189,187, 87, 87, +188, 87, 87, 87, 87, 87, 87,189, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87,190,190,190,190,190,190,190,190,190,190, +191,191,191,192,192,192,192,192,192,193,192, 87, 87, 87, 87, 87, + +/* block 23 */ + 87,194,194,194, 87,195,195,195,195,195,195,195,195, 87,195,195, +195, 87,195,195,195,195,195,195,195,195,195,195,195,195,195,195, +195,195,195,195,195,195,195,195,195, 87,195,195,195,195,195,195, +195,195,195,195, 87,195,195,195,195,195, 87, 87, 87,195,196,196, +196,194,194,194,194, 87,196,196,196, 87,196,196,196,196, 87, 87, + 87, 87, 87, 87, 87,196,196, 87,195,195, 87, 87, 87, 87, 87, 87, +195,195,196,196, 87, 87,197,197,197,197,197,197,197,197,197,197, + 87, 87, 87, 87, 87, 87, 87, 87,198,198,198,198,198,198,198,199, + +/* block 24 */ + 87, 87,200,200, 87,201,201,201,201,201,201,201,201, 87,201,201, +201, 87,201,201,201,201,201,201,201,201,201,201,201,201,201,201, +201,201,201,201,201,201,201,201,201, 87,201,201,201,201,201,201, +201,201,201,201, 87,201,201,201,201,201, 87, 87,202,201,200,202, +200,200,200,200,200, 87,202,200,200, 87,200,200,202,202, 87, 87, + 87, 87, 87, 87, 87,200,200, 87, 87, 87, 87, 87, 87, 87,201, 87, +201,201,202,202, 87, 87,203,203,203,203,203,203,203,203,203,203, + 87, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 25 */ + 87, 87,204,204, 87,205,205,205,205,205,205,205,205, 87,205,205, +205, 87,205,205,205,205,205,205,205,205,205,205,205,205,205,205, +205,205,205,205,205,205,205,205,205, 87,205,205,205,205,205,205, +205,205,205,205,205,205,205,205,205,205, 87, 87, 87,205,204,204, +204,206,206,206,206, 87,204,204,204, 87,204,204,204,206, 87, 87, + 87, 87, 87, 87, 87, 87, 87,204, 87, 87, 87, 87, 87, 87, 87, 87, +205,205,206,206, 87, 87,207,207,207,207,207,207,207,207,207,207, +208,208,208,208,208,208, 87, 87, 87,209,205,205,205,205,205,205, + +/* block 26 */ + 87, 87,210,210, 87,211,211,211,211,211,211,211,211,211,211,211, +211,211,211,211,211,211,211, 87, 87, 87,211,211,211,211,211,211, +211,211,211,211,211,211,211,211,211,211,211,211,211,211,211,211, +211,211, 87,211,211,211,211,211,211,211,211,211, 87,211, 87, 87, +211,211,211,211,211,211,211, 87, 87, 87,212, 87, 87, 87, 87,210, +210,210,212,212,212, 87,212, 87,210,210,210,210,210,210,210,210, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87,210,210,213, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 27 */ + 87,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, +214,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, +214,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, +214,215,214,214,215,215,215,215,215,215,215, 87, 87, 87, 87, 3, +214,214,214,214,214,214,216,215,215,215,215,215,215,215,215,217, +218,218,218,218,218,218,218,218,218,218,217,217, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 28 */ + 87,219,219, 87,219, 87, 87,219,219, 87,219, 87, 87,219, 87, 87, + 87, 87, 87, 87,219,219,219,219, 87,219,219,219,219,219,219,219, + 87,219,219,219, 87,219, 87,219, 87, 87,219,219, 87,219,219,219, +219,220,219,219,220,220,220,220,220,220, 87,220,220,219, 87, 87, +219,219,219,219,219, 87,221, 87,220,220,220,220,220,220, 87, 87, +222,222,222,222,222,222,222,222,222,222, 87, 87,219,219, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 29 */ +223,224,224,224,225,225,225,225,225,225,225,225,225,225,225,225, +225,225,225,224,224,224,224,224,226,226,224,224,224,224,224,224, +227,227,227,227,227,227,227,227,227,227,228,228,228,228,228,228, +228,228,228,228,224,226,224,226,224,226,229,230,229,230,231,231, +223,223,223,223,223,223,223,223, 87,223,223,223,223,223,223,223, +223,223,223,223,223,223,223,223,223,223,223,223,223,223,223,223, +223,223,223,223,223,223,223,223,223,223,223,223,223, 87, 87, 87, + 87,226,226,226,226,226,226,226,226,226,226,226,226,226,226,231, + +/* block 30 */ +226,226,226,226,226,225,226,226,223,223,223,223, 87, 87, 87, 87, +226,226,226,226,226,226,226,226, 87,226,226,226,226,226,226,226, +226,226,226,226,226,226,226,226,226,226,226,226,226,226,226,226, +226,226,226,226,226,226,226,226,226,226,226,226,226, 87,224,224, +224,224,224,224,224,224,226,224,224,224,224,224,224, 87,224,224, +225,225,225,225,225, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 31 */ +232,232,232,232,232,232,232,232,232,232,232,232,232,232,232,232, +232,232,232,232,232,232,232,232,232,232,232,232,232,232,232,232, +232,232,232,232,232,232,232,232,232,232,232,233,233,234,234,234, +234,233,234,234,234,234,234,234,233,234,234,233,233,234,234,232, +235,235,235,235,235,235,235,235,235,235,236,236,236,236,236,236, +232,232,232,232,232,232,233,233,234,234,232,232,232,232,234,234, +234,232,233,233,233,232,232,233,233,233,233,233,233,233,232,232, +232,234,234,234,234,232,232,232,232,232,232,232,232,232,232,232, + +/* block 32 */ +232,232,234,233,233,234,234,233,233,233,233,233,233,234,232,233, +235,235,235,235,235,235,235,235,235,235, 87, 87, 87, 87,237,237, +238,238,238,238,238,238,238,238,238,238,238,238,238,238,238,238, +238,238,238,238,238,238,238,238,238,238,238,238,238,238,238,238, +238,238,238,238,238,238, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,239, +239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,239, +239,239,239,239,239,239,239,239,239,239,239, 2,240, 87, 87, 87, + +/* block 33 */ +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241, 87, 87, 87, 87, 87,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, + +/* block 34 */ +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241, 87, 87, 87, 87, 87,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241, 87, 87, 87, 87, 87, 87, + +/* block 35 */ +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242, 87,242,242,242,242, 87, 87, +242,242,242,242,242,242,242, 87,242, 87,242,242,242,242, 87, 87, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, + +/* block 36 */ +242,242,242,242,242,242,242,242,242, 87,242,242,242,242, 87, 87, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242, 87, +242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, + +/* block 37 */ +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242,242,242,242,242, 87, 87, 87, 87,243, +244,245,245,245,245,245,245,245,245,246,246,246,246,246,246,246, +246,246,246,246,246,246,246,246,246,246,246,246,246, 87, 87, 87, + +/* block 38 */ +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +244,244,244,244,244,244,244,244,244,244, 87, 87, 87, 87, 87, 87, +247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, +247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, +247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, +247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, +247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, +247,247,247,247,247, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 39 */ + 87,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, + +/* block 40 */ +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, + +/* block 41 */ +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, +248,248,248,248,248,248,248,248,248,248,248,248,248,249,249,248, +248,248,248,248,248,248,248, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 42 */ +250,251,251,251,251,251,251,251,251,251,251,251,251,251,251,251, +251,251,251,251,251,251,251,251,251,251,251,252,253, 87, 87, 87, +254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, +254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, +254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, +254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, +254,254,254,254,254,254,254,254,254,254,254, 2, 2, 2,255,255, +255, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 43 */ +256,256,256,256,256,256,256,256,256,256,256,256,256, 87,256,256, +256,256,257,257,257, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258, +258,258,259,259,259, 2, 2, 87, 87, 87, 87, 87, 87, 87, 87, 87, +260,260,260,260,260,260,260,260,260,260,260,260,260,260,260,260, +260,260,261,261, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +262,262,262,262,262,262,262,262,262,262,262,262,262, 87,262,262, +262, 87,263,263, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 44 */ +264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, +264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, +264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, +264,264,264,264,265,265,266,267,267,267,267,267,267,267,266,266, +266,266,266,266,266,266,267,266,266,267,267,267,267,267,267,267, +267,267,267,267,268,268,268,269,268,268,268,270,264,267, 87, 87, +271,271,271,271,271,271,271,271,271,271, 87, 87, 87, 87, 87, 87, +272,272,272,272,272,272,272,272,272,272, 87, 87, 87, 87, 87, 87, + +/* block 45 */ +273,273, 2, 2,273, 2,274,273,273,273,273,275,275,275,276, 87, +277,277,277,277,277,277,277,277,277,277, 87, 87, 87, 87, 87, 87, +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,279,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 46 */ +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, +278,278,278,278,278,278,278,278,278,275,278, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 47 */ +280,280,280,280,280,280,280,280,280,280,280,280,280,280,280,280, +280,280,280,280,280,280,280,280,280,280,280,280,280, 87, 87, 87, +281,281,281,282,282,282,282,281,281,282,282,282, 87, 87, 87, 87, +282,282,281,282,282,282,282,282,282,281,281,281, 87, 87, 87, 87, +283, 87, 87, 87,284,284,285,285,285,285,285,285,285,285,285,285, +286,286,286,286,286,286,286,286,286,286,286,286,286,286,286,286, +286,286,286,286,286,286,286,286,286,286,286,286,286,286, 87, 87, +286,286,286,286,286, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 48 */ +287,287,287,287,287,287,287,287,287,287,287,287,287,287,287,287, +287,287,287,287,287,287,287,287,287,287,287,287,287,287,287,287, +287,287,287,287,287,287,287,287,287,287, 87, 87, 87, 87, 87, 87, +288,288,288,288,288,288,288,288,288,288,288,288,288,288,288,288, +288,287,287,287,287,287,287,287,288,288, 87, 87, 87, 87, 87, 87, +289,289,289,289,289,289,289,289,289,289, 87, 87, 87, 87,290,290, +291,291,291,291,291,291,291,291,291,291,291,291,291,291,291,291, +291,291,291,291,291,291,291,291,291,291,291,291,291,291,291,291, + +/* block 49 */ +292,292,292,292,292,292,292,292,292,292,292,292,292,292,292,292, +292,292,292,292,292,292,292,293,293,294,294,294, 87, 87,295,295, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 50 */ +296,296,296,296,297,298,298,298,298,298,298,298,298,298,298,298, +298,298,298,298,298,298,298,298,298,298,298,298,298,298,298,298, +298,298,298,298,298,298,298,298,298,298,298,298,298,298,298,298, +298,298,298,298,296,297,296,296,296,296,296,297,296,297,297,297, +297,297,296,297,297,298,298,298,298,298,298,298, 87, 87, 87, 87, +299,299,299,299,299,299,299,299,299,299,300,300,300,300,300,300, +300,301,301,301,301,301,301,301,301,301,301,296,296,296,296,296, +296,296,296,296,301,301,301,301,301,301,301,301,301, 87, 87, 87, + +/* block 51 */ +302,302,303,304,304,304,304,304,304,304,304,304,304,304,304,304, +304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304, +304,303,302,302,302,302,303,303,302,302,303, 87, 87, 87,304,304, +305,305,305,305,305,305,305,305,305,305, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 52 */ +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,307,307,307,307,307,307,307,307,308,308,308,308, +308,308,308,308,307,307,308,308, 87, 87, 87,309,309,309,309,309, +310,310,310,310,310,310,310,310,310,310, 87, 87, 87,306,306,306, +311,311,311,311,311,311,311,311,311,311,312,312,312,312,312,312, +312,312,312,312,312,312,312,312,312,312,312,312,312,312,312,312, +312,312,312,312,312,312,312,312,313,313,313,313,313,313,314,314, + +/* block 53 */ + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 94, 94, 94, 94, 94,315, 80, 80, 80, 80, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 88, 88, 88, + 88, 88, 14, 14, 14, 14, 94, 94, 94, 94, 94, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 14, 14,316,317, 14, 14, 14,318, 14, 14, + +/* block 54 */ + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 80, 80, 80, 80, 80, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, + 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 88, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 82, 82, + +/* block 55 */ + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + +/* block 56 */ + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 14, 14, 14, 14, 14,319, 14, 14,320, 14, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + +/* block 57 */ +321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, +321,321,321,321,321,321, 87, 87,322,322,322,322,322,322, 87, 87, +321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, +321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, +321,321,321,321,321,321, 87, 87,322,322,322,322,322,322, 87, 87, + 94,321, 94,321, 94,321, 94,321, 87,322, 87,322, 87,322, 87,322, +321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, +323,323,324,324,324,324,325,325,326,326,327,327,328,328, 87, 87, + +/* block 58 */ +321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, +321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, +321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, +321,321, 94,330, 94, 87, 94, 94,322,322,331,331,332, 86,333, 86, + 86, 86, 94,330, 94, 87, 94, 94,334,334,334,334,332, 86, 86, 86, +321,321, 94, 94, 87, 87, 94, 94,322,322,335,335, 87, 86, 86, 86, +321,321, 94, 94, 94,113, 94, 94,322,322,336,336,117, 86, 86, 86, + 87, 87, 94,330, 94, 87, 94, 94,337,337,338,338,332, 86, 86, 87, + +/* block 59 */ + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 16,339,339, 16, 16, + 7, 7, 7, 7, 7, 7, 2, 2, 15, 19, 4, 15, 15, 19, 4, 15, + 2, 2, 2, 2, 2, 2, 2, 2,340,341, 16, 16, 16, 16, 16, 1, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 15, 19, 2, 2, 2, 2, 11, + 11, 2, 2, 2, 6, 4, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 6, 2, 11, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, + 16, 16, 16, 16, 16, 87, 87, 87, 87, 87, 16, 16, 16, 16, 16, 16, + 17, 14, 87, 87, 17, 17, 17, 17, 17, 17, 6, 6, 6, 4, 5, 14, + +/* block 60 */ + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 6, 6, 6, 4, 5, 87, + 80, 80, 80, 80, 80, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, + 3, 3, 3, 3, 3, 3, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82,342,342,342, +342, 82,342,342,342, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 61 */ + 13, 13,343, 13, 13, 13, 13,343, 13, 13,344,343,343,343,344,344, +343,343,343,344, 13,343, 13, 13, 13,343,343,343,343,343, 13, 13, + 13, 13, 13, 13,343, 13,345, 13,343, 13,346,347,343,343, 13,344, +343,343,348,343,344,349,349,349,349,344, 13, 13,344,344,343,343, + 6, 6, 6, 6, 6,343,344,344,344,344, 13, 6, 13, 13,350, 13, + 87, 87, 87, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, +351,351,351,351,351,351,351,351,351,351,351,351,351,351,351,351, +352,352,352,352,352,352,352,352,352,352,352,352,352,352,352,352, + +/* block 62 */ +353,353,353, 21, 22,353,353,353,353, 87, 87, 87, 87, 87, 87, 87, + 6, 6, 6, 6, 6, 13, 13, 13, 13, 13, 6, 6, 13, 13, 13, 13, + 6, 13, 13, 6, 13, 13, 6, 13, 13, 13, 13, 13, 13, 13, 6, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, + 13, 13, 6, 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + +/* block 63 */ + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + +/* block 64 */ + 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 6, 6, 13, 13, 13, 13, 13, 13, 13, 4, 5, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 13, 13, 13, + +/* block 65 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, + 6, 6, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 66 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + +/* block 67 */ + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13,354,354,354,354,354,354,354,354,354,354, +354,354,354,354,354,354,354,354,354,354,354,354,354,354,354,354, +355,355,355,355,355,355,355,355,355,355,355,355,355,355,355,355, +355,355,355,355,355,355,355,355,355,355, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + +/* block 68 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + +/* block 69 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 6, 6, 6, 6, + +/* block 70 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + +/* block 71 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, + 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 72 */ + 87, 13, 13, 13, 13, 87, 13, 13, 13, 13, 87, 87, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 87, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 13, 87, 13, + 13, 13, 13, 87, 87, 87, 13, 87, 13, 13, 13, 13, 13, 13, 13, 87, + 87, 13, 13, 13, 13, 13, 13, 13, 4, 5, 4, 5, 4, 5, 4, 5, + 4, 5, 4, 5, 4, 5, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + +/* block 73 */ + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 13, 87, 87, 87, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 87, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, + 6, 6, 6, 6, 6, 4, 5, 6, 6, 6, 6, 87, 6, 87, 87, 87, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + +/* block 74 */ +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, +356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, + +/* block 75 */ + 6, 6, 6, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, + 5, 4, 5, 4, 5, 4, 5, 4, 5, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 4, 5, 4, 5, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 4, 5, 6, 6, + +/* block 76 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 13, 13, 6, 6, 6, 6, 6, 6, 87, 87, 87, + 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 77 */ +357,357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, +357,357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, +357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, 87, +358,358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, +358,358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, +358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, 87, + 21, 22,359,360,361,362,363, 21, 22, 21, 22, 21, 22,364,365,366, + 87, 14, 21, 22, 14, 21, 22, 14, 14, 14, 14, 14, 14, 80, 87, 87, + +/* block 78 */ +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, +109,110,109,110,367,368,368,368,368,368,368, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87,369,369,369,369,370,369,369, + +/* block 79 */ +371,371,371,371,371,371,371,371,371,371,371,371,371,371,371,371, +371,371,371,371,371,371,371,371,371,371,371,371,371,371,371,371, +371,371,371,371,371,371, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, +372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, +372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, +372,372,372,372,372,372, 87, 87, 87, 87, 87, 87, 87, 87, 87,373, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 80 */ +242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, +242,242,242,242,242,242,242, 87, 87, 87, 87, 87, 87, 87, 87, 87, +242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, +242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, +242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, +242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, +126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126, +126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126, + +/* block 81 */ + 2, 2, 15, 19, 15, 19, 2, 2, 2, 15, 19, 2, 15, 19, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 7, 2, 15, 19, 2, 2, + 15, 19, 4, 5, 4, 5, 4, 5, 4, 5, 2, 2, 2, 2, 2, 81, + 2, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 82 */ +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374, 87,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 83 */ +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, + +/* block 84 */ +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, +374,374,374,374,374,374, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, + +/* block 85 */ + 1, 2, 2, 2, 13,375,349,376, 4, 5, 4, 5, 4, 5, 4, 5, + 4, 5, 13, 13, 4, 5, 4, 5, 4, 5, 4, 5, 7, 4, 5, 5, + 13,376,376,376,376,376,376,376,376,376, 82, 82, 82, 82, 82, 82, + 7, 81, 81, 81, 81, 81, 13, 13,376,376,376,375,349, 2, 13, 13, + 87,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, +377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, +377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, +377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, + +/* block 86 */ +377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, +377,377,377,377,377,377,377, 87, 87, 82, 82, 10, 10,378,378,377, + 7,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379, 2, 81,380,380,379, + +/* block 87 */ + 87, 87, 87, 87, 87,381,381,381,381,381,381,381,381,381,381,381, +381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, +381,381,381,381,381,381,381,381,381,381,381,381,381,381, 87, 87, + 87,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, + +/* block 88 */ +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, 87, + 13, 13, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, +381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, +381,381,381,381,381,381,381,381, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, + +/* block 89 */ +382,382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, +382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, 87, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, +382,382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, +382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, 13, + +/* block 90 */ + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, 87, + +/* block 91 */ +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, +383,383,383,383,383,383,383,383, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + +/* block 92 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, + +/* block 93 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + +/* block 94 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 95 */ +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,386,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, + +/* block 96 */ +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, + +/* block 97 */ +385,385,385,385,385,385,385,385,385,385,385,385,385, 87, 87, 87, +387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, +387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, +387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, +387,387,387,387,387,387,387, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 98 */ +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, + +/* block 99 */ +388,388,388,388,388,388,388,388,388,388,388,388,389,390,390,390, +388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, +391,391,391,391,391,391,391,391,391,391,388,388, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, + 87, 87,123,124,123,124,123,124,123,124,123,124,123,124,392,126, +127,127,127,393, 87, 87, 87, 87, 87, 87, 87, 87,126,126,393,316, + +/* block 100 */ +123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, +123,124,123,124,123,124,123,124, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 101 */ + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + 10, 10, 10, 10, 10, 10, 10, 81, 81, 81, 81, 81, 81, 81, 81, 81, + 10, 10, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 14, 14, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, + 80, 14, 14, 14, 14, 14, 14, 14, 14, 21, 22, 21, 22,394, 21, 22, + +/* block 102 */ + 21, 22, 21, 22, 21, 22, 21, 22, 81, 10, 10, 21, 22, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 45, 45, 45, 45, 45, + +/* block 103 */ +395,395,396,395,395,395,396,395,395,395,395,396,395,395,395,395, +395,395,395,395,395,395,395,395,395,395,395,395,395,395,395,395, +395,395,395,397,397,396,396,397,398,398,398,398, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, +399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, +399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, +399,399,399,399,400,400,400,400, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 104 */ +401,401,402,402,402,402,402,402,402,402,402,402,402,402,402,402, +402,402,402,402,402,402,402,402,402,402,402,402,402,402,402,402, +402,402,402,402,402,402,402,402,402,402,402,402,402,402,402,402, +402,402,402,402,401,401,401,401,401,401,401,401,401,401,401,401, +401,401,401,401,403, 87, 87, 87, 87, 87, 87, 87, 87, 87,404,404, +405,405,405,405,405,405,405,405,405,405, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 105 */ +406,406,406,406,406,406,406,406,406,406,407,407,407,407,407,407, +407,407,407,407,407,407,407,407,407,407,407,407,407,407,407,407, +407,407,407,407,407,407,408,408,408,408,408,408,408,408,409,409, +410,410,410,410,410,410,410,410,410,410,410,410,410,410,410,410, +410,410,410,410,410,410,410,411,411,411,411,411,411,411,411,411, +411,411,412,412, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,413, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 106 */ +414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414, +414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414, +414,414,414,414,414,414,414,414,414,415,415,415,415,415,415,416, +416,415,415,416,416,415,415, 87, 87, 87, 87, 87, 87, 87, 87, 87, +414,414,414,415,414,414,414,414,414,414,414,414,415,416, 87, 87, +417,417,417,417,417,417,417,417,417,417, 87, 87,418,418,418,418, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 107 */ +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, + +/* block 108 */ +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 109 */ +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, +419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, + +/* block 110 */ +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, + +/* block 111 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384, 87, 87, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384, 87, 87, 87, 87, 87, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, + +/* block 112 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 113 */ + 14, 14, 14, 14, 14, 14, 14, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87,134,134,134,134,134, 87, 87, 87, 87, 87,139,136,139, +139,139,139,139,139,139,139,139,139,421,139,139,139,139,139,139, +139,139,139,139,139,139,139, 87,139,139,139,139,139, 87,139, 87, +139,139, 87,139,139, 87,139,139,139,139,139,139,139,139,139,139, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 114 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 115 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 116 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145, 4, 5, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + +/* block 117 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, + 87, 87,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +145,145,145,145,145,145,145,145,145,145,145,145,142, 13, 87, 87, + +/* block 118 */ + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 87, 87, 87, 87, 87, 87, + 82, 82, 82, 82, 82, 82, 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 2, 7, 7, 11, 11, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, + 5, 4, 5, 4, 5, 2, 2, 4, 5, 2, 2, 2, 2, 11, 11, 11, + 2, 2, 2, 87, 2, 2, 2, 2, 7, 4, 5, 4, 5, 4, 5, 2, + 2, 2, 6, 7, 6, 6, 6, 87, 2, 3, 2, 2, 87, 87, 87, 87, +145,145,145,145,145, 87,145,145,145,145,145,145,145,145,145,145, + +/* block 119 */ +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, +145,145,145,145,145,145,145,145,145,145,145,145,145, 87, 87, 16, + +/* block 120 */ + 87, 2, 2, 2, 3, 2, 2, 2, 4, 5, 2, 6, 2, 7, 2, 2, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 2, 2, 6, 6, 6, 2, + 2, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 2, 5, 10, 11, + 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, + 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 4, 6, 5, 6, 4, + 5, 2, 4, 5, 2, 2,379,379,379,379,379,379,379,379,379,379, + 81,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, + +/* block 121 */ +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379, 81, 81, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, +241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, 87, + 87, 87,241,241,241,241,241,241, 87, 87,241,241,241,241,241,241, + 87, 87,241,241,241,241,241,241, 87, 87,241,241,241, 87, 87, 87, + 3, 3, 6, 10, 13, 3, 3, 87, 13, 6, 6, 6, 6, 13, 13, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 16, 16, 16, 13, 13, 87, 87, + +/* block 122 */ +422,422,422,422,422,422,422,422,422,422,422,422, 87,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422, 87,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422, 87,422,422, 87,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422, 87, 87, +422,422,422,422,422,422,422,422,422,422,422,422,422,422, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 123 */ +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, +422,422,422,422,422,422,422,422,422,422,422, 87, 87, 87, 87, 87, + +/* block 124 */ + 2, 2, 13, 87, 87, 87, 87, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 17, 17, 87, 87, 87, 13, 13, 13, 13, 13, 13, 13, 13, 13, +423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, +423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, +423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, +423,423,423,423,423,424,424,424,424,425,425,425,425,425,425,425, + +/* block 125 */ +425,425,425,425,425,425,425,425,425,425,424, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 82, 87, 87, + +/* block 126 */ +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426, 87, 87, 87, +427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, +427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, +427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, +427, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 127 */ +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, 87, +429,429,429,429, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +430,430,430,430,430,430,430,430,430,430,430,430,430,430,430,430, +430,431,430,430,430,430,430,430,430,430,431, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 128 */ +432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432, +432,432,432,432,432,432,432,432,432,432,432,432,432,432, 87,433, +434,434,434,434,434,434,434,434,434,434,434,434,434,434,434,434, +434,434,434,434,434,434,434,434,434,434,434,434,434,434,434,434, +434,434,434,434, 87, 87, 87, 87,434,434,434,434,434,434,434,434, +435,436,436,436,436,436, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 129 */ +437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, +437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, +437,437,437,437,437,437,437,437,438,438,438,438,438,438,438,438, +438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, +438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, +439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, +439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, +439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, + +/* block 130 */ +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440, 87, 87, +441,441,441,441,441,441,441,441,441,441, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 131 */ +442,442,442,442,442,442, 87, 87,442, 87,442,442,442,442,442,442, +442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, +442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, +442,442,442,442,442,442, 87,442,442, 87, 87, 87,442, 87, 87,442, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 132 */ +443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,443, +443,443,443,443,443,443,444,444,444,444, 87, 87, 87, 87, 87,445, +446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,446, +446,446,446,446,446,446,446,446,446,446, 87, 87, 87, 87, 87,447, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 133 */ +448,449,449,449, 87,449,449, 87, 87, 87, 87, 87,449,449,449,449, +448,448,448,448, 87,448,448,448, 87,448,448,448,448,448,448,448, +448,448,448,448,448,448,448,448,448,448,448,448,448,448,448,448, +448,448,448,448, 87, 87, 87, 87,449,449,449, 87, 87, 87, 87,449, +450,450,450,450,450,450,450,450, 87, 87, 87, 87, 87, 87, 87, 87, +451,451,451,451,451,451,451,451,451, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 134 */ +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, + +/* block 135 */ +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, +452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 136 */ +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, +453,453,453, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, +454,454,454,454, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 137 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 138 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 87, 87, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13,455,455, 82, 82, 82, 13, 13, 13,455,455,455, +455,455,455, 16, 16, 16, 16, 16, 16, 16, 16, 82, 82, 82, 82, 82, + +/* block 139 */ + 82, 82, 82, 13, 13, 82, 82, 82, 82, 82, 82, 82, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 82, 82, 82, 82, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 140 */ +425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, +425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, +425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, +425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, +425,425,456,456,456,425, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 141 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, + 17, 17, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 142 */ +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,344,344, +344,344,344,344,344, 87,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, + +/* block 143 */ +343,343,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,343, 87,343,343, + 87, 87,343, 87, 87,343,343, 87, 87,343,343,343,343, 87,343,343, +343,343,343,343,343,343,344,344,344,344, 87,344, 87,344,344,344, +344,344,344,344, 87,344,344,344,344,344,344,344,344,344,344,344, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, + +/* block 144 */ +344,344,344,344,343,343, 87,343,343,343,343, 87, 87,343,343,343, +343,343,343,343,343, 87,343,343,343,343,343,343,343, 87,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,343,343, 87,343,343,343,343, 87, +343,343,343,343,343, 87,343, 87, 87, 87,343,343,343,343,343,343, +343, 87,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, + +/* block 145 */ +343,343,343,343,343,343,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, + +/* block 146 */ +344,344,344,344,344,344,344,344,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, + +/* block 147 */ +343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344, 87, 87,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343, 6,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344, 6,344,344,344,344, +344,344,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343, 6,344,344,344,344, + +/* block 148 */ +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344, 6,344,344,344,344,344,344,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343, 6,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, 6, +344,344,344,344,344,344,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, 6, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, + +/* block 149 */ +344,344,344,344,344,344,344,344,344, 6,344,344,344,344,344,344, +343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, +343,343,343,343,343,343,343,343,343, 6,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344, 6,344,344,344,344,344,344,343,344, 87, 87, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + +/* block 150 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + +/* block 151 */ + 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 152 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 153 */ +384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, +384,384,384,384,384,384,384,384,384,384,384,384,384,384, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 154 */ + 87, 16, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + +/* block 155 */ + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + +/* block 156 */ + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, + 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, + +/* block 157 */ +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, +420,420,420,420,420,420,420,420,420,420,420,420,420,420, 87, 87, + +}; + +#if UCD_BLOCK_SIZE != 128 +#error Please correct UCD_BLOCK_SIZE in pcre_internal.h +#endif Modified: freeswitch/trunk/libs/pcre/pcre_valid_utf8.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_valid_utf8.c (original) +++ freeswitch/trunk/libs/pcre/pcre_valid_utf8.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,6 +42,10 @@ strings. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -55,6 +59,13 @@ can be turned off for maximum performance, but the consequences of supplying an invalid string are then undefined. +Originally, this function checked according to RFC 2279, allowing for values in +the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in +the canonical format. Once somebody had pointed out RFC 3629 to me (it +obsoletes 2279), additional restrictions were applied. The values are now +limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the +subrange 0xd000 to 0xdfff is excluded. + Arguments: string points to the string length length of string, or -1 if the string is zero-terminated @@ -64,9 +75,10 @@ */ int -_pcre_valid_utf8(const uschar *string, int length) +_pcre_valid_utf8(USPTR string, int length) { -register const uschar *p; +#ifdef SUPPORT_UTF8 +register USPTR p; if (length < 0) { @@ -79,32 +91,49 @@ register int ab; register int c = *p; if (c < 128) continue; - if ((c & 0xc0) != 0xc0) return p - string; - ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ - if (length < ab) return p - string; + if (c < 0xc0) return p - string; + ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ + if (length < ab || ab > 3) return p - string; length -= ab; /* Check top bits in the second byte */ if ((*(++p) & 0xc0) != 0x80) return p - string; - /* Check for overlong sequences for each different length */ + /* Check for overlong sequences for each different length, and for the + excluded range 0xd000 to 0xdfff. */ + switch (ab) { - /* Check for xx00 000x */ + /* Check for xx00 000x (overlong sequence) */ + case 1: if ((c & 0x3e) == 0) return p - string; continue; /* We know there aren't any more bytes to check */ - /* Check for 1110 0000, xx0x xxxx */ + /* Check for 1110 0000, xx0x xxxx (overlong sequence) or + 1110 1101, 1010 xxxx (0xd000 - 0xdfff) */ + case 2: - if (c == 0xe0 && (*p & 0x20) == 0) return p - string; + if ((c == 0xe0 && (*p & 0x20) == 0) || + (c == 0xed && *p >= 0xa0)) + return p - string; break; - /* Check for 1111 0000, xx00 xxxx */ + /* Check for 1111 0000, xx00 xxxx (overlong sequence) or + greater than 0x0010ffff (f4 8f bf bf) */ + case 3: - if (c == 0xf0 && (*p & 0x30) == 0) return p - string; + if ((c == 0xf0 && (*p & 0x30) == 0) || + (c > 0xf4 ) || + (c == 0xf4 && *p > 0x8f)) + return p - string; break; +#if 0 + /* These cases can no longer occur, as we restrict to a maximum of four + bytes nowadays. Leave the code here in case we ever want to add an option + for longer sequences. */ + /* Check for 1111 1000, xx00 0xxx */ case 4: if (c == 0xf8 && (*p & 0x38) == 0) return p - string; @@ -115,6 +144,8 @@ if (c == 0xfe || c == 0xff || (c == 0xfc && (*p & 0x3c) == 0)) return p - string; break; +#endif + } /* Check for valid bytes after the 2nd, if any; all must start 10 */ @@ -123,6 +154,10 @@ if ((*(++p) & 0xc0) != 0x80) return p - string; } } +#else +(void)(string); /* Keep picky compilers happy */ +(void)(length); +#endif return -1; } Modified: freeswitch/trunk/libs/pcre/pcre_version.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_version.c (original) +++ freeswitch/trunk/libs/pcre/pcre_version.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2008 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,6 +42,10 @@ string that identifies the PCRE version that is in use. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -49,16 +53,38 @@ * Return version string * *************************************************/ +/* These macros are the standard way of turning unquoted text into C strings. +They allow macros like PCRE_MAJOR to be defined without quotes, which is +convenient for user programs that want to test its value. */ + #define STRING(a) # a #define XSTRING(s) STRING(s) -PCRE_DATA_SCOPE const char * +/* A problem turned up with PCRE_PRERELEASE, which is defined empty for +production releases. Originally, it was used naively in this code: + + return XSTRING(PCRE_MAJOR) + "." XSTRING(PCRE_MINOR) + XSTRING(PCRE_PRERELEASE) + " " XSTRING(PCRE_DATE); + +However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of +STRING(). The C standard states: "If (before argument substitution) any +argument consists of no preprocessing tokens, the behavior is undefined." It +turns out the gcc treats this case as a single empty string - which is what we +really want - but Visual C grumbles about the lack of an argument for the +macro. Unfortunately, both are within their rights. To cope with both ways of +handling this, I had resort to some messy hackery that does a test at run time. +I could find no way of detecting that a macro is defined as an empty string at +pre-processor time. This hack uses a standard trick for avoiding calling +the STRING macro with an empty argument when doing the test. */ + +PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION pcre_version(void) { -return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); +return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? + XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : + XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); } /* End of pcre_version.c */ Modified: freeswitch/trunk/libs/pcre/pcre_xclass.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcre_xclass.c (original) +++ freeswitch/trunk/libs/pcre/pcre_xclass.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -39,10 +39,13 @@ /* This module contains an internal function that is used to match an extended -class (one that contains characters whose values are > 255). It is used by both -pcre_exec() and pcre_def_exec(). */ +class. It is used by both pcre_exec() and pcre_def_exec(). */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include "pcre_internal.h" @@ -51,7 +54,7 @@ *************************************************/ /* This function is called to match a character against an extended class that -might contain values > 255. +might contain values > 255 and/or Unicode properties. Arguments: c the character @@ -100,8 +103,7 @@ #ifdef SUPPORT_UCP else /* XCL_PROP & XCL_NOTPROP */ { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); + const ucd_record *prop = GET_UCD(c); switch(*data) { @@ -110,20 +112,20 @@ break; case PT_LAMP: - if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) == + if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt) == (t == XCL_PROP)) return !negated; break; case PT_GC: - if ((data[1] == category) == (t == XCL_PROP)) return !negated; + if ((data[1] == _pcre_ucp_gentype[prop->chartype]) == (t == XCL_PROP)) return !negated; break; case PT_PC: - if ((data[1] == chartype) == (t == XCL_PROP)) return !negated; + if ((data[1] == prop->chartype) == (t == XCL_PROP)) return !negated; break; case PT_SC: - if ((data[1] == script) == (t == XCL_PROP)) return !negated; + if ((data[1] == prop->script) == (t == XCL_PROP)) return !negated; break; /* This should never occur, but compilers may mutter if there is no Modified: freeswitch/trunk/libs/pcre/pcrecpp.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcrecpp.cc (original) +++ freeswitch/trunk/libs/pcre/pcrecpp.cc Mon Jun 8 18:51:30 2009 @@ -29,6 +29,10 @@ // // Author: Sanjay Ghemawat +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <stdlib.h> #include <stdio.h> #include <ctype.h> @@ -37,13 +41,11 @@ #include <errno.h> #include <string> #include <algorithm> -#include "config.h" -// We need this to compile the proper dll on windows/msys. This is copied -// from pcre_internal.h. It would probably be better just to include that. -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ + +#include "pcrecpp_internal.h" #include "pcre.h" -#include "pcre_stringpiece.h" #include "pcrecpp.h" +#include "pcre_stringpiece.h" namespace pcrecpp { @@ -53,7 +55,23 @@ static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace // Special object that stands-in for no argument -Arg no_arg((void*)NULL); +Arg RE::no_arg((void*)NULL); + +// This is for ABI compatibility with old versions of pcre (pre-7.6), +// which defined a global no_arg variable instead of putting it in the +// RE class. This works on GCC >= 3, at least. It definitely works +// for ELF, but may not for other object formats (Mach-O, for +// instance, does not support aliases.) We could probably have a more +// inclusive test if we ever needed it. (Note that not only the +// __attribute__ syntax, but also __USER_LABEL_PREFIX__, are +// gnu-specific.) +#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) +# define ULP_AS_STRING(x) ULP_AS_STRING_INTERNAL(x) +# define ULP_AS_STRING_INTERNAL(x) #x +# define USER_LABEL_PREFIX_STR ULP_AS_STRING(__USER_LABEL_PREFIX__) +extern Arg no_arg + __attribute__((alias(USER_LABEL_PREFIX_STR "_ZN7pcrecpp2RE6no_argE"))); +#endif // If a regular expression has no error, its error_ field points here static const string empty_string; @@ -61,7 +79,7 @@ // If the user doesn't ask for any options, we just use this one static RE_Options default_options; -void RE::Init(const char* pat, const RE_Options* options) { +void RE::Init(const string& pat, const RE_Options* options) { pattern_ = pat; if (options == NULL) { options_ = default_options; @@ -74,27 +92,22 @@ re_partial_ = Compile(UNANCHORED); if (re_partial_ != NULL) { - // Check for complicated patterns. The following change is - // conservative in that it may treat some "simple" patterns - // as "complex" (e.g., if the vertical bar is in a character - // class or is escaped). But it seems good enough. - if (strchr(pat, '|') == NULL) { - // Simple pattern: we can use position-based checks to perform - // fully anchored matches - re_full_ = re_partial_; - } else { - // We need a special pattern for anchored matches - re_full_ = Compile(ANCHOR_BOTH); - } + re_full_ = Compile(ANCHOR_BOTH); } } +void RE::Cleanup() { + if (re_full_ != NULL) (*pcre_free)(re_full_); + if (re_partial_ != NULL) (*pcre_free)(re_partial_); + if (error_ != &empty_string) delete error_; +} + + RE::~RE() { - if (re_full_ != NULL && re_full_ != re_partial_) (*pcre_free)(re_full_); - if (re_partial_ != NULL) (*pcre_free)(re_partial_); - if (error_ != &empty_string) delete error_; + Cleanup(); } + pcre* RE::Compile(Anchor anchor) { // First, convert RE_Options into pcre options int pcre_options = 0; @@ -334,13 +347,17 @@ // Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF. // Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF. +// Modified by PH to add PCRE_NEWLINE_ANY and PCRE_NEWLINE_ANYCRLF. + static int NewlineMode(int pcre_options) { // TODO: if we can make it threadsafe, cache this var int newline_mode = 0; /* if (newline_mode) return newline_mode; */ // do this once it's cached - if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)) { + if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| + PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)) { newline_mode = (pcre_options & - (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)); + (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| + PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)); } else { int newline; pcre_config(PCRE_CONFIG_NEWLINE, &newline); @@ -350,8 +367,12 @@ newline_mode = PCRE_NEWLINE_CR; else if (newline == 3338) newline_mode = PCRE_NEWLINE_CRLF; + else if (newline == -1) + newline_mode = PCRE_NEWLINE_ANY; + else if (newline == -2) + newline_mode = PCRE_NEWLINE_ANYCRLF; else - assert("" == "Unexpected return value from pcre_config(NEWLINE)"); + assert(NULL == "Unexpected return value from pcre_config(NEWLINE)"); } return newline_mode; } @@ -364,7 +385,7 @@ int start = 0; int lastend = -1; - for (; start <= static_cast<int>(str->length()); count++) { + while (start <= static_cast<int>(str->length())) { int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize); if (matches <= 0) break; @@ -379,9 +400,13 @@ // Note it's better to call pcre_fullinfo() than to examine // all_options(), since options_ could have changed bewteen // compile-time and now, but this is simpler and safe enough. + // Modified by PH to add ANY and ANYCRLF. if (start+1 < static_cast<int>(str->length()) && (*str)[start] == '\r' && (*str)[start+1] == '\n' && - NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF) { + (NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF || + NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANY || + NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANYCRLF) + ) { matchend++; } // We also need to advance more than one char if we're in utf8 mode. @@ -424,6 +449,40 @@ return Rewrite(out, rewrite, text, vec, matches); } +/*static*/ string RE::QuoteMeta(const StringPiece& unquoted) { + string result; + + // Escape any ascii character not in [A-Za-z_0-9]. + // + // Note that it's legal to escape a character even if it has no + // special meaning in a regular expression -- so this function does + // that. (This also makes it identical to the perl function of the + // same name; see `perldoc -f quotemeta`.) The one exception is + // escaping NUL: rather than doing backslash + NUL, like perl does, + // we do '\0', because pcre itself doesn't take embedded NUL chars. + for (int ii = 0; ii < unquoted.size(); ++ii) { + // Note that using 'isalnum' here raises the benchmark time from + // 32ns to 58ns: + if (unquoted[ii] == '\0') { + result += "\\0"; + } else if ((unquoted[ii] < 'a' || unquoted[ii] > 'z') && + (unquoted[ii] < 'A' || unquoted[ii] > 'Z') && + (unquoted[ii] < '0' || unquoted[ii] > '9') && + unquoted[ii] != '_' && + // If this is the part of a UTF8 or Latin1 character, we need + // to copy this byte without escaping. Experimentally this is + // what works correctly with the regexp library. + !(unquoted[ii] & 128)) { + result += '\\'; + result += unquoted[ii]; + } else { + result += unquoted[ii]; + } + } + + return result; +} + /***** Actual matching and rewriting code *****/ int RE::TryMatch(const StringPiece& text, @@ -437,7 +496,7 @@ return 0; } - pcre_extra extra = { 0 }; + pcre_extra extra = { 0, 0, 0, 0, 0, 0 }; if (options_.match_limit() > 0) { extra.flags |= PCRE_EXTRA_MATCH_LIMIT; extra.match_limit = options_.match_limit(); @@ -470,13 +529,6 @@ rc = vecsize / 2; } - if ((anchor == ANCHOR_BOTH) && (re_full_ == re_partial_)) { - // We need an extra check to make sure that the match extended - // to the end of the input string - assert(vec[0] == 0); // PCRE_ANCHORED forces starting match - if (vec[1] != text.size()) return 0; // Did not get ending match - } - return rc; } @@ -553,14 +605,14 @@ if (start >= 0) out->append(text.data() + start, vec[2 * n + 1] - start); } else if (c == '\\') { - out->push_back('\\'); + *out += '\\'; } else { //fprintf(stderr, "invalid rewrite pattern: %.*s\n", // rewrite.size(), rewrite.data()); return false; } } else { - out->push_back(c); + *out += c; } } return true; @@ -588,23 +640,27 @@ } bool Arg::parse_string(const char* str, int n, void* dest) { + if (dest == NULL) return true; reinterpret_cast<string*>(dest)->assign(str, n); return true; } bool Arg::parse_stringpiece(const char* str, int n, void* dest) { + if (dest == NULL) return true; reinterpret_cast<StringPiece*>(dest)->set(str, n); return true; } bool Arg::parse_char(const char* str, int n, void* dest) { if (n != 1) return false; + if (dest == NULL) return true; *(reinterpret_cast<char*>(dest)) = str[0]; return true; } bool Arg::parse_uchar(const char* str, int n, void* dest) { if (n != 1) return false; + if (dest == NULL) return true; *(reinterpret_cast<unsigned char*>(dest)) = str[0]; return true; } @@ -653,6 +709,7 @@ long r = strtol(str, &end, radix); if (end != str + n) return false; // Leftover junk if (errno) return false; + if (dest == NULL) return true; *(reinterpret_cast<long*>(dest)) = r; return true; } @@ -670,6 +727,7 @@ unsigned long r = strtoul(str, &end, radix); if (end != str + n) return false; // Leftover junk if (errno) return false; + if (dest == NULL) return true; *(reinterpret_cast<unsigned long*>(dest)) = r; return true; } @@ -681,7 +739,8 @@ long r; if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range - *(reinterpret_cast<short*>(dest)) = r; + if (dest == NULL) return true; + *(reinterpret_cast<short*>(dest)) = static_cast<short>(r); return true; } @@ -692,7 +751,8 @@ unsigned long r; if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse if (r > USHRT_MAX) return false; // Out of range - *(reinterpret_cast<unsigned short*>(dest)) = r; + if (dest == NULL) return true; + *(reinterpret_cast<unsigned short*>(dest)) = static_cast<unsigned short>(r); return true; } @@ -703,6 +763,7 @@ long r; if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse if (r < INT_MIN || r > INT_MAX) return false; // Out of range + if (dest == NULL) return true; *(reinterpret_cast<int*>(dest)) = r; return true; } @@ -714,6 +775,7 @@ unsigned long r; if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse if (r > UINT_MAX) return false; // Out of range + if (dest == NULL) return true; *(reinterpret_cast<unsigned int*>(dest)) = r; return true; } @@ -734,11 +796,14 @@ long long r = strtoq(str, &end, radix); #elif defined HAVE_STRTOLL long long r = strtoll(str, &end, radix); +#elif defined HAVE__STRTOI64 + long long r = _strtoi64(str, &end, radix); #else #error parse_longlong_radix: cannot convert input to a long-long #endif if (end != str + n) return false; // Leftover junk if (errno) return false; + if (dest == NULL) return true; *(reinterpret_cast<long long*>(dest)) = r; return true; #endif /* HAVE_LONG_LONG */ @@ -761,11 +826,14 @@ unsigned long long r = strtouq(str, &end, radix); #elif defined HAVE_STRTOLL unsigned long long r = strtoull(str, &end, radix); +#elif defined HAVE__STRTOI64 + unsigned long long r = _strtoui64(str, &end, radix); #else #error parse_ulonglong_radix: cannot convert input to a long-long #endif if (end != str + n) return false; // Leftover junk if (errno) return false; + if (dest == NULL) return true; *(reinterpret_cast<unsigned long long*>(dest)) = r; return true; #endif /* HAVE_UNSIGNED_LONG_LONG */ @@ -783,6 +851,7 @@ double r = strtod(buf, &end); if (end != buf + n) return false; // Leftover junk if (errno) return false; + if (dest == NULL) return true; *(reinterpret_cast<double*>(dest)) = r; return true; } @@ -790,6 +859,7 @@ bool Arg::parse_float(const char* str, int n, void* dest) { double r; if (!parse_double(str, n, &r)) return false; + if (dest == NULL) return true; *(reinterpret_cast<float*>(dest)) = static_cast<float>(r); return true; } @@ -809,14 +879,14 @@ return parse_##name##_radix(str, n, dest, 0); \ } -DEFINE_INTEGER_PARSERS(short); -DEFINE_INTEGER_PARSERS(ushort); -DEFINE_INTEGER_PARSERS(int); -DEFINE_INTEGER_PARSERS(uint); -DEFINE_INTEGER_PARSERS(long); -DEFINE_INTEGER_PARSERS(ulong); -DEFINE_INTEGER_PARSERS(longlong); -DEFINE_INTEGER_PARSERS(ulonglong); +DEFINE_INTEGER_PARSERS(short) /* */ +DEFINE_INTEGER_PARSERS(ushort) /* */ +DEFINE_INTEGER_PARSERS(int) /* Don't use semicolons after these */ +DEFINE_INTEGER_PARSERS(uint) /* statements because they can cause */ +DEFINE_INTEGER_PARSERS(long) /* compiler warnings if the checking */ +DEFINE_INTEGER_PARSERS(ulong) /* level is turned up high enough. */ +DEFINE_INTEGER_PARSERS(longlong) /* */ +DEFINE_INTEGER_PARSERS(ulonglong) /* */ #undef DEFINE_INTEGER_PARSERS Modified: freeswitch/trunk/libs/pcre/pcrecpp.h ============================================================================== --- freeswitch/trunk/libs/pcre/pcrecpp.h (original) +++ freeswitch/trunk/libs/pcre/pcrecpp.h Mon Jun 8 18:51:30 2009 @@ -112,6 +112,12 @@ // T (where "bool T::ParseFrom(const char*, int)" exists) // NULL (the corresponding matched sub-pattern is not copied) // +// CAVEAT: An optional sub-pattern that does not exist in the matched +// string is assigned the empty string. Therefore, the following will +// return false (because the empty string is not a valid number): +// int number; +// pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); +// // ----------------------------------------------------------------------- // DO_MATCH // @@ -325,11 +331,10 @@ #include <string> -#include <pcrecpparg.h> // defines the Arg class -// These aren't technically needed here, but we include them -// anyway so folks who include pcrecpp.h don't have to include -// all these other header files as well. #include <pcre.h> +#include <pcrecpparg.h> // defines the Arg class +// This isn't technically needed here, but we include it +// anyway so folks who include pcrecpp.h don't have to. #include <pcre_stringpiece.h> namespace pcrecpp { @@ -341,16 +346,13 @@ #define PCRE_IS_SET(o) \ (all_options_ & o) == o -// We convert user-passed pointers into special Arg objects -extern Arg no_arg; - /***** Compiling regular expressions: the RE class *****/ // RE_Options allow you to set options to be passed along to pcre, // along with other options we put on top of pcre. // Only 9 modifiers, plus match_limit and match_limit_recursion, // are supported now. -class RE_Options { +class PCRECPP_EXP_DEFN RE_Options { public: // constructor RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} @@ -398,25 +400,25 @@ return PCRE_IS_SET(PCRE_DOTALL); } RE_Options &set_dotall(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_DOTALL); + PCRE_SET_OR_CLEAR(x, PCRE_DOTALL); } bool extended() const { return PCRE_IS_SET(PCRE_EXTENDED); } RE_Options &set_extended(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED); + PCRE_SET_OR_CLEAR(x, PCRE_EXTENDED); } bool dollar_endonly() const { return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); } RE_Options &set_dollar_endonly(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY); + PCRE_SET_OR_CLEAR(x, PCRE_DOLLAR_ENDONLY); } bool extra() const { - return PCRE_IS_SET( PCRE_EXTRA); + return PCRE_IS_SET(PCRE_EXTRA); } RE_Options &set_extra(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); @@ -482,14 +484,37 @@ // Interface for regular expression matching. Also corresponds to a // pre-compiled regular expression. An "RE" object is safe for // concurrent use by multiple threads. -class RE { +class PCRECPP_EXP_DEFN RE { public: // We provide implicit conversions from strings so that users can // pass in a string or a "const char*" wherever an "RE" is expected. + RE(const string& pat) { Init(pat, NULL); } + RE(const string& pat, const RE_Options& option) { Init(pat, &option); } RE(const char* pat) { Init(pat, NULL); } - RE(const char *pat, const RE_Options& option) { Init(pat, &option); } - RE(const string& pat) { Init(pat.c_str(), NULL); } - RE(const string& pat, const RE_Options& option) { Init(pat.c_str(), &option); } + RE(const char* pat, const RE_Options& option) { Init(pat, &option); } + RE(const unsigned char* pat) { + Init(reinterpret_cast<const char*>(pat), NULL); + } + RE(const unsigned char* pat, const RE_Options& option) { + Init(reinterpret_cast<const char*>(pat), &option); + } + + // Copy constructor & assignment - note that these are expensive + // because they recompile the expression. + RE(const RE& re) { Init(re.pattern_, &re.options_); } + const RE& operator=(const RE& re) { + if (this != &re) { + Cleanup(); + + // This is the code that originally came from Google + // Init(re.pattern_.c_str(), &re.options_); + + // This is the replacement from Ari Pollak + Init(re.pattern_, &re.options_); + } + return *this; + } + ~RE(); @@ -589,6 +614,18 @@ const StringPiece &text, string *out) const; + // Escapes all potentially meaningful regexp characters in + // 'unquoted'. The returned string, used as a regular expression, + // will exactly match the original string. For example, + // 1.5-2.0? + // may become: + // 1\.5\-2\.0\? + // Note QuoteMeta behaves the same as perl's QuoteMeta function, + // *except* that it escapes the NUL character (\0) as backslash + 0, + // rather than backslash + NUL. + static string QuoteMeta(const StringPiece& unquoted); + + /***** Generic matching interface *****/ // Type of match (TODO: Should be restructured as part of RE_Options) @@ -609,9 +646,19 @@ // regexp wasn't valid on construction. int NumberOfCapturingGroups() const; + // The default value for an argument, to indicate the end of the argument + // list. This must be used only in optional argument defaults. It should NOT + // be passed explicitly. Some people have tried to use it like this: + // + // FullMatch(x, y, &z, no_arg, &w); + // + // This is a mistake, and will not work. + static Arg no_arg; + private: - void Init(const char* pattern, const RE_Options* options); + void Init(const string& pattern, const RE_Options* options); + void Cleanup(); // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with // pairs of integers for the beginning and end positions of matched @@ -655,11 +702,6 @@ pcre* re_full_; // For full matches pcre* re_partial_; // For partial matches const string* error_; // Error indicator (or points to empty string) - - // Don't allow the default copy or assignment constructors -- - // they're expensive and too easy to do by accident. - RE(const RE&); - void operator=(const RE&); }; } // namespace pcrecpp Added: freeswitch/trunk/libs/pcre/pcrecpp_internal.h ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcrecpp_internal.h Mon Jun 8 18:51:30 2009 @@ -0,0 +1,71 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* +Copyright (c) 2005, Google Inc. +All rights reserved. + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +#ifndef PCRECPP_INTERNAL_H +#define PCRECPP_INTERNAL_H + +/* When compiling a DLL for Windows, the exported symbols have to be declared +using some MS magic. I found some useful information on this web page: +http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the +information there, using __declspec(dllexport) without "extern" we have a +definition; with "extern" we have a declaration. The settings here override the +setting in pcre.h. We use: + + PCRECPP_EXP_DECL for declarations + PCRECPP_EXP_DEFN for definitions of exported functions + +*/ + +#ifndef PCRECPP_EXP_DECL +# ifdef _WIN32 +# ifndef PCRE_STATIC +# define PCRECPP_EXP_DECL extern __declspec(dllexport) +# define PCRECPP_EXP_DEFN __declspec(dllexport) +# else +# define PCRECPP_EXP_DECL extern +# define PCRECPP_EXP_DEFN +# endif +# else +# define PCRECPP_EXP_DECL extern +# define PCRECPP_EXP_DEFN +# endif +#endif + +#endif /* PCRECPP_INTERNAL_H */ + +/* End of pcrecpp_internal.h */ Modified: freeswitch/trunk/libs/pcre/pcrecpp_unittest.cc ============================================================================== --- freeswitch/trunk/libs/pcre/pcrecpp_unittest.cc (original) +++ freeswitch/trunk/libs/pcre/pcrecpp_unittest.cc Mon Jun 8 18:51:30 2009 @@ -1,4 +1,6 @@ -// Copyright (c) 2005, Google Inc. +// -*- coding: utf-8 -*- +// +// Copyright (c) 2005 - 2006, Google Inc. // All rights reserved. // // Redistribution and use in source and binary forms, with or without @@ -31,10 +33,13 @@ // // TODO: Test extractions for PartialMatch/Consume +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <stdio.h> #include <cassert> #include <vector> -#include "config.h" #include "pcrecpp.h" using pcrecpp::StringPiece; @@ -105,8 +110,8 @@ initial_size = VirtualProcessSize(); printf("Size after 50000: %llu\n", initial_size); } - char buf[100]; - snprintf(buf, sizeof(buf), "pat%09d", i); + char buf[100]; // definitely big enough + sprintf(buf, "pat%09d", i); RE newre(buf); } uint64 final_size = VirtualProcessSize(); @@ -208,87 +213,103 @@ const char *original; const char *single; const char *global; + int global_count; // the expected return value from ReplaceAll }; static const ReplaceTest tests[] = { { "(qu|[b-df-hj-np-tv-z]*)([a-z]+)", "\\2\\1ay", "the quick brown fox jumps over the lazy dogs.", "ethay quick brown fox jumps over the lazy dogs.", - "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday." }, + "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday.", + 9 }, { "\\w+", "\\0-NOSPAM", "paul.haahr@google.com", "paul-NOSPAM.haahr@google.com", - "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM" }, + "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM", + 4 }, { "^", "(START)", "foo", "(START)foo", - "(START)foo" }, + "(START)foo", + 1 }, { "^", "(START)", "", "(START)", - "(START)" }, + "(START)", + 1 }, { "$", "(END)", "", "(END)", - "(END)" }, + "(END)", + 1 }, { "b", "bb", "ababababab", "abbabababab", - "abbabbabbabbabb" }, + "abbabbabbabbabb", + 5 }, { "b", "bb", "bbbbbb", "bbbbbbb", - "bbbbbbbbbbbb" }, + "bbbbbbbbbbbb", + 6 }, { "b+", "bb", "bbbbbb", "bb", - "bb" }, + "bb", + 1 }, { "b*", "bb", "bbbbbb", "bb", - "bb" }, + "bb", + 1 }, { "b*", "bb", "aaaaa", "bbaaaaa", - "bbabbabbabbabbabb" }, + "bbabbabbabbabbabb", + 6 }, { "b*", "bb", "aa\naa\n", "bbaa\naa\n", - "bbabbabb\nbbabbabb\nbb" }, + "bbabbabb\nbbabbabb\nbb", + 7 }, { "b*", "bb", "aa\raa\r", "bbaa\raa\r", - "bbabbabb\rbbabbabb\rbb" }, + "bbabbabb\rbbabbabb\rbb", + 7 }, { "b*", "bb", "aa\r\naa\r\n", "bbaa\r\naa\r\n", - "bbabbabb\r\nbbabbabb\r\nbb" }, + "bbabbabb\r\nbbabbabb\r\nbb", + 7 }, #ifdef SUPPORT_UTF8 { "b*", "bb", "\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", // utf8 "bb\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", - "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb" }, + "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb", + 5 }, { "b*", "bb", "\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", // utf8 "bb\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", ("bb\xE3\x83\x9B""bb\r\nbb""\xE3\x83\xBC""bb\rbb""\xE3\x83\xA0" - "bb\nbb""\xE3\x81\xB8""bb\r\nbb") }, + "bb\nbb""\xE3\x81\xB8""bb\r\nbb"), + 9 }, #endif - { "", NULL, NULL, NULL, NULL } + { "", NULL, NULL, NULL, NULL, 0 } }; #ifdef SUPPORT_UTF8 @@ -304,8 +325,9 @@ CHECK(re.Replace(t->rewrite, &one)); CHECK_EQ(one, t->single); string all(t->original); - CHECK(re.GlobalReplace(t->rewrite, &all) > 0); + const int replace_count = re.GlobalReplace(t->rewrite, &all); CHECK_EQ(all, t->global); + CHECK_EQ(replace_count, t->global_count); } // One final test: test \r\n replacement when we're not in CRLF mode @@ -313,14 +335,14 @@ RE re("b*", RE_Options(PCRE_NEWLINE_CR).set_utf8(support_utf8)); assert(re.error().empty()); string all("aa\r\naa\r\n"); - CHECK(re.GlobalReplace("bb", &all) > 0); + CHECK_EQ(re.GlobalReplace("bb", &all), 9); CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); } { RE re("b*", RE_Options(PCRE_NEWLINE_LF).set_utf8(support_utf8)); assert(re.error().empty()); string all("aa\r\naa\r\n"); - CHECK(re.GlobalReplace("bb", &all) > 0); + CHECK_EQ(re.GlobalReplace("bb", &all), 9); CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); } // TODO: test what happens when no PCRE_NEWLINE_* flag is set. @@ -445,6 +467,81 @@ CHECK(re4.FullMatch(text_bad) == false); } +// A meta-quoted string, interpreted as a pattern, should always match +// the original unquoted string. +static void TestQuoteMeta(string unquoted, RE_Options options = RE_Options()) { + string quoted = RE::QuoteMeta(unquoted); + RE re(quoted, options); + CHECK(re.FullMatch(unquoted)); +} + +// A string containing meaningful regexp characters, which is then meta- +// quoted, should not generally match a string the unquoted string does. +static void NegativeTestQuoteMeta(string unquoted, string should_not_match, + RE_Options options = RE_Options()) { + string quoted = RE::QuoteMeta(unquoted); + RE re(quoted, options); + CHECK(!re.FullMatch(should_not_match)); +} + +// Tests that quoted meta characters match their original strings, +// and that a few things that shouldn't match indeed do not. +static void TestQuotaMetaSimple() { + TestQuoteMeta("foo"); + TestQuoteMeta("foo.bar"); + TestQuoteMeta("foo\\.bar"); + TestQuoteMeta("[1-9]"); + TestQuoteMeta("1.5-2.0?"); + TestQuoteMeta("\\d"); + TestQuoteMeta("Who doesn't like ice cream?"); + TestQuoteMeta("((a|b)c?d*e+[f-h]i)"); + TestQuoteMeta("((?!)xxx).*yyy"); + TestQuoteMeta("(["); + TestQuoteMeta(string("foo\0bar", 7)); +} + +static void TestQuoteMetaSimpleNegative() { + NegativeTestQuoteMeta("foo", "bar"); + NegativeTestQuoteMeta("...", "bar"); + NegativeTestQuoteMeta("\\.", "."); + NegativeTestQuoteMeta("\\.", ".."); + NegativeTestQuoteMeta("(a)", "a"); + NegativeTestQuoteMeta("(a|b)", "a"); + NegativeTestQuoteMeta("(a|b)", "(a)"); + NegativeTestQuoteMeta("(a|b)", "a|b"); + NegativeTestQuoteMeta("[0-9]", "0"); + NegativeTestQuoteMeta("[0-9]", "0-9"); + NegativeTestQuoteMeta("[0-9]", "[9]"); + NegativeTestQuoteMeta("((?!)xxx)", "xxx"); +} + +static void TestQuoteMetaLatin1() { + TestQuoteMeta("3\xb2 = 9"); +} + +static void TestQuoteMetaUtf8() { +#ifdef SUPPORT_UTF8 + TestQuoteMeta("Pl\xc3\xa1\x63ido Domingo", pcrecpp::UTF8()); + TestQuoteMeta("xyz", pcrecpp::UTF8()); // No fancy utf8 + TestQuoteMeta("\xc2\xb0", pcrecpp::UTF8()); // 2-byte utf8 (degree symbol) + TestQuoteMeta("27\xc2\xb0 degrees", pcrecpp::UTF8()); // As a middle character + TestQuoteMeta("\xe2\x80\xb3", pcrecpp::UTF8()); // 3-byte utf8 (double prime) + TestQuoteMeta("\xf0\x9d\x85\x9f", pcrecpp::UTF8()); // 4-byte utf8 (music note) + TestQuoteMeta("27\xc2\xb0"); // Interpreted as Latin-1, but should still work + NegativeTestQuoteMeta("27\xc2\xb0", // 2-byte utf (degree symbol) + "27\\\xc2\\\xb0", + pcrecpp::UTF8()); +#endif +} + +static void TestQuoteMetaAll() { + printf("Testing QuoteMeta\n"); + TestQuotaMetaSimple(); + TestQuoteMetaSimpleNegative(); + TestQuoteMetaLatin1(); + TestQuoteMetaUtf8(); +} + // // Options tests contributed by // Giuseppe Maxia, CTO, Stardata s.r.l. @@ -667,6 +764,35 @@ Test_all_options(); } +static void TestConstructors() { + printf("Testing constructors\n"); + + RE_Options options; + options.set_dotall(true); + const char *str = "HELLO\n" "cruel\n" "world"; + + RE orig("HELLO.*world", options); + CHECK(orig.FullMatch(str)); + + RE copy1(orig); + CHECK(copy1.FullMatch(str)); + + RE copy2("not a match"); + CHECK(!copy2.FullMatch(str)); + copy2 = copy1; + CHECK(copy2.FullMatch(str)); + copy2 = orig; + CHECK(copy2.FullMatch(str)); + + // Make sure when we assign to ourselves, nothing bad happens + orig = orig; + copy1 = copy1; + copy2 = copy2; + CHECK(orig.FullMatch(str)); + CHECK(copy1.FullMatch(str)); + CHECK(copy2.FullMatch(str)); +} + int main(int argc, char** argv) { // Treat any flag as --help if (argc > 1 && argv[1][0] == '-') { @@ -701,8 +827,11 @@ /***** FullMatch with no args *****/ CHECK(RE("h.*o").FullMatch("hello")); - CHECK(!RE("h.*o").FullMatch("othello")); - CHECK(!RE("h.*o").FullMatch("hello!")); + CHECK(!RE("h.*o").FullMatch("othello")); // Must be anchored at front + CHECK(!RE("h.*o").FullMatch("hello!")); // Must be anchored at end + CHECK(RE("a*").FullMatch("aaaa")); // Fullmatch with normal op + CHECK(RE("a*?").FullMatch("aaaa")); // Fullmatch with nongreedy op + CHECK(RE("a*?\\z").FullMatch("aaaa")); // Two unusual ops /***** FullMatch with args *****/ @@ -746,6 +875,24 @@ CHECK_EQ(s, string("ruby")); CHECK_EQ(i, 1234); + // Ignore non-void* NULL arg + CHECK(RE("he(.*)lo").FullMatch("hello", (char*)NULL)); + CHECK(RE("h(.*)o").FullMatch("hello", (string*)NULL)); + CHECK(RE("h(.*)o").FullMatch("hello", (StringPiece*)NULL)); + CHECK(RE("(.*)").FullMatch("1234", (int*)NULL)); +#ifdef HAVE_LONG_LONG + CHECK(RE("(.*)").FullMatch("1234567890123456", (long long*)NULL)); +#endif + CHECK(RE("(.*)").FullMatch("123.4567890123456", (double*)NULL)); + CHECK(RE("(.*)").FullMatch("123.4567890123456", (float*)NULL)); + + // Fail on non-void* NULL arg if the match doesn't parse for the given type. + CHECK(!RE("h(.*)lo").FullMatch("hello", &s, (char*)NULL)); + CHECK(!RE("(.*)").FullMatch("hello", (int*)NULL)); + CHECK(!RE("(.*)").FullMatch("1234567890123456", (int*)NULL)); + CHECK(!RE("(.*)").FullMatch("hello", (double*)NULL)); + CHECK(!RE("(.*)").FullMatch("hello", (float*)NULL)); + // Ignored arg CHECK(RE("(\\w+)(:)(\\d+)").FullMatch("ruby:1234", &s, (void*)NULL, &i)); CHECK_EQ(s, string("ruby")); @@ -797,27 +944,34 @@ CHECK(!RE("(\\d+)").FullMatch("4294967296", &v)); } #ifdef HAVE_LONG_LONG +# if defined(__MINGW__) || defined(__MINGW32__) +# define LLD "%I64d" +# define LLU "%I64u" +# else +# define LLD "%lld" +# define LLU "%llu" +# endif { long long v; static const long long max_value = 0x7fffffffffffffffLL; static const long long min_value = -max_value - 1; - char buf[32]; + char buf[32]; // definitely big enough for a long long CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); CHECK(RE("(-?\\d+)").FullMatch("-100",&v)); CHECK_EQ(v, -100); - snprintf(buf, sizeof(buf), "%lld", max_value); + sprintf(buf, LLD, max_value); CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - snprintf(buf, sizeof(buf), "%lld", min_value); + sprintf(buf, LLD, min_value); CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, min_value); - snprintf(buf, sizeof(buf), "%lld", max_value); + sprintf(buf, LLD, max_value); assert(buf[strlen(buf)-1] != '9'); buf[strlen(buf)-1]++; CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - snprintf(buf, sizeof(buf), "%lld", min_value); + sprintf(buf, LLD, min_value); assert(buf[strlen(buf)-1] != '9'); buf[strlen(buf)-1]++; CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); @@ -828,12 +982,12 @@ unsigned long long v; long long v2; static const unsigned long long max_value = 0xffffffffffffffffULL; - char buf[32]; + char buf[32]; // definitely big enough for a unsigned long long CHECK(RE("(-?\\d+)").FullMatch("100",&v)); CHECK_EQ(v, 100); CHECK(RE("(-?\\d+)").FullMatch("-100",&v2)); CHECK_EQ(v2, -100); - snprintf(buf, sizeof(buf), "%llu", max_value); + sprintf(buf, LLU, max_value); CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); assert(buf[strlen(buf)-1] != '9'); @@ -985,11 +1139,14 @@ CHECK(RE("h.*o").PartialMatch("hello!")); CHECK(RE("((((((((((((((((((((x))))))))))))))))))))").PartialMatch("x")); + /***** other tests *****/ + RadixTests(); TestReplace(); TestExtract(); TestConsume(); TestFindAndConsume(); + TestQuoteMetaAll(); TestMatchNumberPeculiarity(); // Check the pattern() accessor @@ -1011,13 +1168,13 @@ printf("Testing UTF-8 handling\n"); // Three Japanese characters (nihongo) - const char utf8_string[] = { + const unsigned char utf8_string[] = { 0xe6, 0x97, 0xa5, // 65e5 0xe6, 0x9c, 0xac, // 627c 0xe8, 0xaa, 0x9e, // 8a9e 0 }; - const char utf8_pattern[] = { + const unsigned char utf8_pattern[] = { '.', 0xe6, 0x9c, 0xac, // 627c '.', @@ -1109,6 +1266,9 @@ VERBOSE_TEST = true; TestOptions(); + // Test the constructors + TestConstructors(); + // Done printf("OK\n"); Modified: freeswitch/trunk/libs/pcre/pcrecpparg.h.in ============================================================================== --- freeswitch/trunk/libs/pcre/pcrecpparg.h.in (original) +++ freeswitch/trunk/libs/pcre/pcrecpparg.h.in Mon Jun 8 18:51:30 2009 @@ -35,6 +35,8 @@ #include <stdlib.h> // for NULL #include <string> +#include <pcre.h> + namespace pcrecpp { class StringPiece; @@ -46,12 +48,13 @@ class _RE_MatchObject { public: static inline bool Parse(const char* str, int n, void* dest) { + if (dest == NULL) return true; T* object = reinterpret_cast<T*>(dest); return object->ParseFrom(str, n); } }; -class Arg { +class PCRECPP_EXP_DEFN Arg { public: // Empty constructor so we can declare arrays of Arg Arg(); @@ -148,17 +151,17 @@ inline Arg CRadix(type* ptr) { \ return Arg(ptr, Arg::parse_ ## name ## _cradix); } -MAKE_INTEGER_PARSER(short, short); -MAKE_INTEGER_PARSER(unsigned short, ushort); -MAKE_INTEGER_PARSER(int, int); -MAKE_INTEGER_PARSER(unsigned int, uint); -MAKE_INTEGER_PARSER(long, long); -MAKE_INTEGER_PARSER(unsigned long, ulong); -#if @pcre_have_long_long@ -MAKE_INTEGER_PARSER(long long, longlong); -#endif -#if @pcre_have_ulong_long@ -MAKE_INTEGER_PARSER(unsigned long long, ulonglong); +MAKE_INTEGER_PARSER(short, short) /* */ +MAKE_INTEGER_PARSER(unsigned short, ushort) /* */ +MAKE_INTEGER_PARSER(int, int) /* Don't use semicolons */ +MAKE_INTEGER_PARSER(unsigned int, uint) /* after these statement */ +MAKE_INTEGER_PARSER(long, long) /* because they can cause */ +MAKE_INTEGER_PARSER(unsigned long, ulong) /* compiler warnings if */ +#if @pcre_have_long_long@ /* the checking level is */ +MAKE_INTEGER_PARSER(long long, longlong) /* turned up high enough. */ +#endif /* */ +#if @pcre_have_ulong_long@ /* */ +MAKE_INTEGER_PARSER(unsigned long long, ulonglong) /* */ #endif #undef PCRE_IS_SET Modified: freeswitch/trunk/libs/pcre/pcredemo.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcredemo.c (original) +++ freeswitch/trunk/libs/pcre/pcredemo.c Mon Jun 8 18:51:30 2009 @@ -4,17 +4,27 @@ /* This is a demonstration program to illustrate the most straightforward ways of calling the PCRE regular expression library from a C program. See the -pcresample documentation for a short discussion. +pcresample documentation for a short discussion ("man pcresample" if you have +the PCRE man pages installed). + +In Unix-like environments, compile this program thuswise: -Compile thuswise: gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ -R/usr/local/lib -lpcre Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and -library files for PCRE are installed on your system. Only some operating +library files for PCRE are installed on your system. You don't need -I and -L +if PCRE is installed in the standard system libraries. Only some operating systems (e.g. Solaris) use the -R option. -*/ +Building under Windows: + +If you want to statically link this program against a non-dll .a file, you must +define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and +pcre_free() exported functions will be declared __declspec(dllimport), with +unwanted results. So in this environment, uncomment the following line. */ + +/* #define PCRE_STATIC */ #include <stdio.h> #include <string.h> @@ -128,8 +138,8 @@ /************************************************************************* * We have found the first match within the subject string. If the output * -* vector wasn't big enough, set its size to the maximum. Then output any * -* substrings that were captured. * +* vector wasn't big enough, say so. Then output any substrings that were * +* captured. * *************************************************************************/ /* The output vector wasn't big enough */ @@ -154,7 +164,7 @@ /************************************************************************** * That concludes the basic part of this demonstration program. We have * * compiled a pattern, and performed a single match. The code that follows * -* first shows how to access named substrings, and then how to code for * +* shows first how to access named substrings, and then how to code for * * repeated matches on the same subject. * **************************************************************************/ Added: freeswitch/trunk/libs/pcre/pcregexp.pas ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/pcregexp.pas Mon Jun 8 18:51:30 2009 @@ -0,0 +1,820 @@ +{ + pcRegExp - Perl compatible regular expressions for Virtual Pascal + (c) 2001 Peter S. Voronov aka Chem O'Dun <petervrn@yahoo.com> + + Based on PCRE library interface unit for Virtual Pascal. + (c) 2001 Alexander Tokarev <dwalin@dwalin.ru> + + The current PCRE version is: 3.7 + + This software must be distributed as Freeware. + + The PCRE library is written by: Philip Hazel <ph10@cam.ac.uk> + Copyright (c) 1997-2004 University of Cambridge + + AngelsHolocaust 4-11-04 updated to use version v5.0 + (INFO: this is regex-directed, NFA) + AH: 9-11-04 - pcre_free: removed var, pcre already gives the ptr, now + everything works as it should (no more crashes) + -> removed CheckRegExp because pcre handles errors perfectly + 10-11-04 - added pcError (errorhandling), pcInit + 13-11-04 - removed the ErrorPos = 0 check -> always print erroroffset + 17-10-05 - support for \1-\9 backreferences in TpcRegExp.GetReplStr + 17-02-06 - added RunTimeOptions: caller can set options while searching + 19-02-06 - added SearchOfs(): let PCRE use the complete string and offset + into the string itself + 20-12-06 - support for version 7.0 + 27.08.08 - support for v7.7 +} + +{$H+} {$DEFINE PCRE_3_7} {$DEFINE PCRE_5_0} {$DEFINE PCRE_7_0} {$DEFINE PCRE_7_7} + +Unit pcregexp; + +Interface + +uses objects; + +Type + PpcRegExp = ^TpcRegExp; +// TpcRegExp = object + TpcRegExp = object(TObject) + MatchesCount: integer; + RegExpC, RegExpExt : Pointer; + Matches:Pointer; + RegExp: shortstring; + SourceLen: integer; + PartialMatch : boolean; + Error : boolean; + ErrorMsg : Pchar; + ErrorPos : integer; + RunTimeOptions: Integer; // options which can be set by the caller + constructor Init(const ARegExp : shortstring; AOptions : integer; ALocale : Pointer); + function Search(AStr: Pchar; ALen : longint) : boolean; virtual; + function SearchNext( AStr: Pchar; ALen : longint) : boolean; virtual; + function SearchOfs ( AStr: Pchar; ALen, AOfs : longint) : boolean; virtual; + function MatchSub(ANom: integer; var Pos, Len : longint) : boolean; virtual; + function MatchFull(var Pos, Len : longint) : boolean; virtual; + function GetSubStr(ANom: integer; AStr: Pchar) : string; virtual; + function GetFullStr(AStr: Pchar) : string; virtual; + function GetReplStr(AStr: Pchar; const ARepl: string) : string; virtual; + function GetPreSubStr(AStr: Pchar) : string; virtual; + function GetPostSubStr(AStr: Pchar) : string; virtual; + function ErrorStr : string; virtual; + destructor Done; virtual; + end; + + function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean; + function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string; + + function pcFastGrepMatch(WildCard, aStr: string): Boolean; + function pcFastGrepSub(WildCard, aStr, aRepl: string): string; + +{$IFDEF PCRE_5_0} + function pcGetVersion : pchar; +{$ENDIF} + + function pcError (var pRegExp : Pointer) : Boolean; + function pcInit (const Pattern: Shortstring; CaseSens: Boolean) : Pointer; + +Const { Options } + PCRE_CASELESS = $0001; + PCRE_MULTILINE = $0002; + PCRE_DOTALL = $0004; + PCRE_EXTENDED = $0008; + PCRE_ANCHORED = $0010; + PCRE_DOLLAR_ENDONLY = $0020; + PCRE_EXTRA = $0040; + PCRE_NOTBOL = $0080; + PCRE_NOTEOL = $0100; + PCRE_UNGREEDY = $0200; + PCRE_NOTEMPTY = $0400; +{$IFDEF PCRE_5_0} + PCRE_UTF8 = $0800; + PCRE_NO_AUTO_CAPTURE = $1000; + PCRE_NO_UTF8_CHECK = $2000; + PCRE_AUTO_CALLOUT = $4000; + PCRE_PARTIAL = $8000; +{$ENDIF} +{$IFDEF PCRE_7_0} + PCRE_DFA_SHORTEST = $00010000; + PCRE_DFA_RESTART = $00020000; + PCRE_FIRSTLINE = $00040000; + PCRE_DUPNAMES = $00080000; + PCRE_NEWLINE_CR = $00100000; + PCRE_NEWLINE_LF = $00200000; + PCRE_NEWLINE_CRLF = $00300000; + PCRE_NEWLINE_ANY = $00400000; + PCRE_NEWLINE_ANYCRLF = $00500000; + + PCRE_NEWLINE_BITS = PCRE_NEWLINE_CR or PCRE_NEWLINE_LF or PCRE_NEWLINE_ANY; + +{$ENDIF} +{$IFDEF PCRE_7_7} + PCRE_BSR_ANYCRLF = $00800000; + PCRE_BSR_UNICODE = $01000000; + PCRE_JAVASCRIPT_COMPAT= $02000000; +{$ENDIF} + + PCRE_COMPILE_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_AUTO_CALLOUT + PCRE_CASELESS + + PCRE_DOLLAR_ENDONLY + PCRE_DOTALL + PCRE_EXTENDED + + PCRE_EXTRA + PCRE_MULTILINE + PCRE_NO_AUTO_CAPTURE + + PCRE_UNGREEDY + PCRE_UTF8 + PCRE_NO_UTF8_CHECK + {$IFDEF PCRE_7_0} + + PCRE_DUPNAMES + PCRE_FIRSTLINE + PCRE_NEWLINE_BITS + {$ENDIF} + {$IFDEF PCRE_7_7} + + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + PCRE_JAVASCRIPT_COMPAT + {$ENDIF} + ; + + PCRE_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL + + PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL + {$IFDEF PCRE_7_0} + + PCRE_NEWLINE_BITS + {$ENDIF} + {$IFDEF PCRE_7_7} + + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + {$ENDIF} + ; + +{$IFDEF PCRE_7_0} + PCRE_DFA_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL + + PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL + + PCRE_DFA_SHORTEST + PCRE_DFA_RESTART + + PCRE_NEWLINE_BITS + {$IFDEF PCRE_7_7} + + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + {$ENDIF} + ; +{$ENDIF} + +{ Exec-time and get/set-time error codes } + PCRE_ERROR_NOMATCH = -1; + PCRE_ERROR_NULL = -2; + PCRE_ERROR_BADOPTION = -3; + PCRE_ERROR_BADMAGIC = -4; + PCRE_ERROR_UNKNOWN_MODE = -5; + PCRE_ERROR_NOMEMORY = -6; + PCRE_ERROR_NOSUBSTRING = -7; +{$IFDEF PCRE_5_0} + PCRE_ERROR_MATCHLIMIT = -8; + PCRE_ERROR_CALLOUT = -9; { Never used by PCRE itself } + PCRE_ERROR_BADUTF8 = -10; + PCRE_ERROR_BADUTF8_OFFSET = -11; + PCRE_ERROR_PARTIAL = -12; + PCRE_ERROR_BADPARTIAL = -13; + PCRE_ERROR_INTERNAL = -14; + PCRE_ERROR_BADCOUNT = -15; +{$ENDIF} +{$IFDEF PCRE_7_0} + PCRE_ERROR_DFA_UITEM = -16; + PCRE_ERROR_DFA_UCOND = -17; + PCRE_ERROR_DFA_UMLIMIT = -18; + PCRE_ERROR_DFA_WSSIZE = -19; + PCRE_ERROR_DFA_RECURSE = -20; + PCRE_ERROR_RECURSIONLIMIT = -21; + PCRE_ERROR_NULLWSLIMIT = -22; + PCRE_ERROR_BADNEWLINE = -23; +{$ENDIF} + +{ Request types for pcre_fullinfo() } + + PCRE_INFO_OPTIONS = 0; + PCRE_INFO_SIZE = 1; + PCRE_INFO_CAPTURECOUNT = 2; + PCRE_INFO_BACKREFMAX = 3; + PCRE_INFO_FIRSTBYTE = 4; + PCRE_INFO_FIRSTCHAR = 4; { For backwards compatibility } + PCRE_INFO_FIRSTTABLE = 5; +{$IFDEF PCRE_5_0} + PCRE_INFO_LASTLITERAL = 6; + PCRE_INFO_NAMEENTRYSIZE = 7; + PCRE_INFO_NAMECOUNT = 8; + PCRE_INFO_NAMETABLE = 9; + PCRE_INFO_STUDYSIZE = 10; + PCRE_INFO_DEFAULT_TABLES = 11; +{$ENDIF PCRE_5_0} +{$IFDEF PCRE_7_7} + PCRE_INFO_OKPARTIAL = 12; + PCRE_INFO_JCHANGED = 13; + PCRE_INFO_HASCRORLF = 14; +{$ENDIF} + +{ Request types for pcre_config() } +{$IFDEF PCRE_5_0} + PCRE_CONFIG_UTF8 = 0; + PCRE_CONFIG_NEWLINE = 1; + PCRE_CONFIG_LINK_SIZE = 2; + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD = 3; + PCRE_CONFIG_MATCH_LIMIT = 4; + PCRE_CONFIG_STACKRECURSE = 5; + PCRE_CONFIG_UNICODE_PROPERTIES = 6; +{$ENDIF PCRE_5_0} +{$IFDEF PCRE_7_0} + PCRE_CONFIG_MATCH_LIMIT_RECURSION = 7; +{$ENDIF} +{$IFDEF PCRE_7_7} + PCRE_CONFIG_BSR = 8; +{$ENDIF} + +{ Bit flags for the pcre_extra structure } +{$IFDEF PCRE_5_0} + PCRE_EXTRA_STUDY_DATA = $0001; + PCRE_EXTRA_MATCH_LIMIT = $0002; + PCRE_EXTRA_CALLOUT_DATA = $0004; + PCRE_EXTRA_TABLES = $0008; +{$ENDIF PCRE_5_0} +{$IFDEF PCRE_7_0} + PCRE_EXTRA_MATCH_LIMIT_RECURSION = $0010; +{$ENDIF} + +Const +// DefaultOptions : integer = 0; + DefaultLocaleTable : pointer = nil; + +{$IFDEF PCRE_5_0} +{ The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. } + +type ppcre_extra = ^tpcre_extra; + tpcre_extra = record + flags : longint; { Bits for which fields are set } + study_data : pointer; { Opaque data from pcre_study() } + match_limit : longint; { Maximum number of calls to match() } + callout_data : pointer; { Data passed back in callouts } + tables : pointer; { Pointer to character tables } + match_limit_recursion: longint; { Max recursive calls to match() } + end; + +type ppcre_callout_block = ^pcre_callout_block; + pcre_callout_block = record + version, + (* ------------------------ Version 0 ------------------------------- *) + callout_number : integer; + offset_vector : pointer; + subject : pchar; + subject_length, start_match, current_position, capture_top, + capture_last : integer; + callout_data : pointer; + (* ------------------- Added for Version 1 -------------------------- *) + pattern_position, next_item_length : integer; + end; +{$ENDIF PCRE_5_0} + +{$OrgName+} +{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL} + + { local replacement of external pcre memory management functions } + function pcre_malloc( size : integer ) : pointer; + procedure pcre_free( {var} p : pointer ); +{$IFDEF PCRE_5_0} + const pcre_stack_malloc: function ( size : integer ): pointer = pcre_malloc; + pcre_stack_free: procedure ( {var} p : pointer ) = pcre_free; + function pcre_callout(var p : ppcre_callout_block) : integer; +{$ENDIF PCRE_5_0} +{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL} + +Implementation + +Uses strings, collect, messages, dnapp, commands, advance0, stringsx + {$IFDEF VIRTUALPASCAL} ,vpsyslow {$ENDIF VIRTUALPASCAL}; + +Const + MAGIC_NUMBER = $50435245; { 'PCRE' } + MAX_MATCHES = 90; { changed in 3.5 version; should be divisible by 3, was 64} + +Type + PMatchArray = ^TMatchArray; + TMatchArray = array[0..( MAX_MATCHES * 3 )] of integer; + + PRegExpCollection = ^TRegExpCollection; + TRegExpCollection = object(TSortedCollection) + MaxRegExp : integer; + SearchRegExp : shortstring; + CompareModeInsert : boolean; + constructor Init(AMaxRegExp:integer); + procedure FreeItem(P: Pointer); virtual; + function Compare(P1, P2: Pointer): Integer; virtual; + function Find(ARegExp:shortstring;var P: PpcRegExp):boolean; virtual; + function CheckNew(ARegExp:shortstring):PpcRegExp;virtual; + end; + +Var + PRegExpCache : PRegExpCollection; + + +{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL} + + { imported original pcre functions } + + function pcre_compile( const pattern : PChar; options : integer; + var errorptr : PChar; var erroroffset : integer; + const tables : PChar ) : pointer {pcre}; external; +{$IFDEF PCRE_7_0} + function pcre_compile2( const pattern : PChar; options : integer; + var errorcodeptr : Integer; + var errorptr : PChar; var erroroffset : integer; + const tables : PChar ) : pointer {pcre}; external; +{$ENDIF} +{$IFDEF PCRE_5_0} + function pcre_config( what : integer; where : pointer) : integer; external; + function pcre_copy_named_substring( const code : pointer {pcre}; + const subject : pchar; + var ovector : integer; + stringcount : integer; + const stringname : pchar; + var buffer : pchar; + size : integer) : integer; external; + function pcre_copy_substring( const subject : pchar; var ovector : integer; + stringcount, stringnumber : integer; + var buffer : pchar; size : integer ) + : integer; external; + function pcre_exec( const argument_re : pointer {pcre}; + const extra_data : pointer {pcre_extra}; +{$ELSE} + function pcre_exec( const external_re : pointer; + const external_extra : pointer; +{$ENDIF} + const subject : PChar; + length, start_offset, options : integer; + offsets : pointer; + offsetcount : integer ) : integer; external; +{$IFDEF PCRE_7_0} + function pcre_dfa_exec( const argument_re : pointer {pcre}; + const extra_data : pointer {pcre_extra}; + const subject : pchar; + length, start_offset, options : integer; + offsets : pointer; + offsetcount : integer; + workspace : pointer; + wscount : integer ) : integer; external; +{$ENDIF} +{$IFDEF PCRE_5_0} + procedure pcre_free_substring( const p : pchar ); external; + procedure pcre_free_substring_list( var p : pchar ); external; + function pcre_fullinfo( const argument_re : pointer {pcre}; + const extra_data : pointer {pcre_extra}; + what : integer; + where : pointer ) : integer; external; + function pcre_get_named_substring( const code : pointer {pcre}; + const subject : pchar; + var ovector : integer; + stringcount : integer; + const stringname : pchar; + var stringptr : pchar ) : integer; external; + function pcre_get_stringnumber( const code : pointer {pcre}; + const stringname : pchar ) : integer; external; + function pcre_get_stringtable_entries( const code : pointer {pcre}; + const stringname : pchar; + var firstptr, + lastptr : pchar ) : integer; external; + function pcre_get_substring( const subject : pchar; var ovector : integer; + stringcount, stringnumber : integer; + var stringptr : pchar ) : integer; external; + function pcre_get_substring_list( const subject : pchar; var ovector : integer; + stringcount : integer; + listptr : pointer {const char ***listptr}) : integer; external; + function pcre_info( const argument_re : pointer {pcre}; + var optptr : integer; + var first_byte : integer ) : integer; external; + function pcre_maketables : pchar; external; +{$ENDIF} +{$IFDEF PCRE_7_0} + function pcre_refcount( const argument_re : pointer {pcre}; + adjust : integer ) : pchar; external; +{$ENDIF} + function pcre_study( const external_re : pointer {pcre}; + options : integer; + var errorptr : PChar ) : pointer {pcre_extra}; external; +{$IFDEF PCRE_5_0} + function pcre_version : pchar; external; +{$ENDIF} + + function pcre_malloc( size : integer ) : pointer; + begin + GetMem( result, size ); + end; + + procedure pcre_free( {var} p : pointer ); + begin + if (p <> nil) then + FreeMem( p, 0 ); + {@p := nil;} + end; + +{$IFDEF PCRE_5_0} +(* Called from PCRE as a result of the (?C) item. We print out where we are in +the match. Yield zero unless more callouts than the fail count, or the callout +data is not zero. *) + + function pcre_callout; + begin + end; +{$ENDIF} + +{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL} + +// Always include the newest version of the library +{$IFDEF PCRE_7_7} + {$L pcre77.lib} +{$ELSE} + {$IFDEF PCRE_7_0} + {$L pcre70.lib} + {$ELSE} + {$IFDEF PCRE_5_0} + {$L pcre50.lib} + {$ELSE} + {$IFDEF PCRE_3_7} + {$L pcre37.lib} + {$ENDIF PCRE_3_7} + {$ENDIF PCRE_5_0} + {$ENDIF PCRE_7_0} +{$ENDIF PCRE_7_7} + +{TpcRegExp} + + constructor TpcRegExp.Init(const ARegExp:shortstring; AOptions:integer; ALocale : Pointer); + var + pRegExp : PChar; + begin + RegExp:=ARegExp; + RegExpC:=nil; + RegExpExt:=nil; + Matches:=nil; + MatchesCount:=0; + Error:=true; + ErrorMsg:=nil; + ErrorPos:=0; + RunTimeOptions := 0; + if length(RegExp) < 255 then + begin + RegExp[length(RegExp)+1]:=#0; + pRegExp:=@RegExp[1]; + end + else + begin + GetMem(pRegExp,length(RegExp)+1); + pRegExp:=strpcopy(pRegExp,RegExp); + end; + RegExpC := pcre_compile( pRegExp, + AOptions and PCRE_COMPILE_ALLOWED_OPTIONS, + ErrorMsg, ErrorPos, ALocale); + if length(RegExp) = 255 then + StrDispose(pRegExp); + if RegExpC = nil then + exit; + ErrorMsg:=nil; + RegExpExt := pcre_study( RegExpC, 0, ErrorMsg ); + if (RegExpExt = nil) and (ErrorMsg <> nil) then + begin + pcre_free(RegExpC); + exit; + end; + GetMem(Matches,SizeOf(TMatchArray)); + Error:=false; + end; + + destructor TpcRegExp.Done; + begin + if RegExpC <> nil then + pcre_free(RegExpC); + if RegExpExt <> nil then + pcre_free(RegExpExt); + if Matches <> nil then + FreeMem(Matches,SizeOf(TMatchArray)); + end; + + function TpcRegExp.SearchNext( AStr: Pchar; ALen : longint ) : boolean; + var Options: Integer; + begin // must handle PCRE_ERROR_PARTIAL here + Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and + PCRE_EXEC_ALLOWED_OPTIONS; + if MatchesCount > 0 then + MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, PMatchArray(Matches)^[1], + Options, Matches, MAX_MATCHES ) else + MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, 0, + Options, Matches, MAX_MATCHES ); +{ if MatchesCount = 0 then + MatchesCount := MatchesCount div 3;} + PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL; + SearchNext := MatchesCount > 0; + end; + + function TpcRegExp.Search( AStr: Pchar; ALen : longint):boolean; + begin + MatchesCount:=0; + Search:=SearchNext(AStr,ALen); + SourceLen:=ALen; + end; + + function TpcRegExp.SearchOfs( AStr: Pchar; ALen, AOfs: longint ) : boolean; + var Options: Integer; + begin + MatchesCount:=0; + Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and + PCRE_EXEC_ALLOWED_OPTIONS; + MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, AOfs, + Options, Matches, MAX_MATCHES ); + PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL; + SearchOfs := MatchesCount > 0; + SourceLen := ALen-AOfs; + end; + + function TpcRegExp.MatchSub(ANom:integer; var Pos,Len:longint):boolean; + begin + if (MatchesCount > 0) and (ANom <= (MatchesCount-1)) then + begin + ANom:=ANom*2; + Pos:=PMatchArray(Matches)^[ANom]; + Len:=PMatchArray(Matches)^[ANom+1]-Pos; + MatchSub:=true; + end + else + MatchSub:=false; + end; + + function TpcRegExp.MatchFull(var Pos,Len:longint):boolean; + begin + MatchFull:=MatchSub(0,Pos,Len); + end; + + function TpcRegExp.GetSubStr(ANom: integer; AStr: Pchar):string; + var + s: ansistring; + pos,len: longint; + begin + s:=''; + if MatchSub(ANom, pos, len) then + begin + setlength(s, len); + Move(AStr[pos], s[1], len); + end; + GetSubStr:=s; + end; + + function TpcRegExp.GetPreSubStr(AStr: Pchar):string; + var + s: ansistring; + l: longint; + begin + s:=''; + if (MatchesCount > 0) then + begin + l:=PMatchArray(Matches)^[0]-1; + if l > 0 then + begin + setlength(s,l); + Move(AStr[1],s[1],l); + end; + end; + GetPreSubStr:=s; + end; + + function TpcRegExp.GetPostSubStr(AStr: Pchar):string; + var + s: ansistring; + l: longint; + ANom: integer; + begin + s:=''; + if (MatchesCount > 0) then + begin + ANom:=(MatchesCount-1){*2} shl 1; + l:=SourceLen-PMatchArray(Matches)^[ANom+1]+1; + if l > 0 then + begin + setlength(s,l); + Move(AStr[PMatchArray(Matches)^[ANom+1]],s[1],l); + end; + end; + GetPostSubStr:=s; + end; + + + function TpcRegExp.GetFullStr(AStr: Pchar):string; + var + s: ansistring; + l: longint; + begin + GetFullStr:=GetSubStr(0,AStr); + end; + + function TpcRegExp.GetReplStr(AStr: Pchar; const ARepl: string):string; + var + s: ansistring; + l,i,lasti: longint; + begin + l:=length(ARepl); + i:=1; + lasti:=1; + s:=''; + while i <= l do + begin + case ARepl[i] of + '\' : + begin + if i < l then + begin + s:=s+copy(ARepl,lasti,i-lasti){+ARepl[i+1]}; + {AH 17-10-05 support for POSIX \1-\9 backreferences} + case ARepl[i+1] of + '0' : s:=s+GetFullStr(AStr); + '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr); + else s:=s+ARepl[i+1]; // copy the escaped character + end; + end; + inc(i); + lasti:=i+1; + end; + '$' : + begin + if i < l then + begin + s:=s+copy(ARepl,lasti,i-lasti); + case ARepl[i+1] of + '&' : s:=s+GetFullStr(AStr); + '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr); + '`' : s:=s+GetPreSubStr(AStr); + #39 : s:=s+GetPostSubStr(AStr); + end; + end; + inc(i); + lasti:=i+1; + end; + end; + inc(i); + end; + if lasti <= {AH 25-10-2004 added =, else l==1 won't work} l then + s:=s+copy(ARepl,lasti,l-lasti+1); + GetReplStr:=s; + end; + + function TpcRegExp.ErrorStr:string; + begin + ErrorStr:=StrPas(ErrorMsg); + end; + +{TRegExpCollection} + +constructor TRegExpCollection.Init(AMaxRegExp: integer); +begin + Inherited Init(1,1); + MaxRegExp:=AMaxRegExp; + CompareModeInsert:=true; +end; + +procedure TRegExpCollection.FreeItem(P: Pointer); +begin + if P <> nil then + begin + Dispose(PpcRegExp(P),Done); + end; +end; + +function TRegExpCollection.Compare(P1, P2: Pointer): Integer; +//var +// l,l1,l2,i : byte; +//// wPos: pchar; +begin + if CompareModeInsert then + begin +// l1:=length(PpcRegExp(P1)^.RegExp); +// l2:=length(PpcRegExp(P2)^.RegExp); +// if l1 > l2 then l:=l2 else +// l:=l1; +// for i:=1 to l do +// if PpcRegExp(P1).RegExp[i] <> PpcRegExp(P2).RegExp[i] then break; +// if i <=l then +// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(PpcRegExp(P2).RegExp[i]) else +// Compare:=l1-l2; + Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, PpcRegExp(P2).RegExp, False); + end + else + begin +// l1:=length(PpcRegExp(P1)^.RegExp); +// l2:=length(SearchRegExp); +// if l1 > l2 then l:=l2 else +// l:=l1; +// for i:=1 to l do +// if PpcRegExp(P1).RegExp[i] <> SearchRegExp[i] then +// begin +// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(SearchRegExp[i]); +// break; +// end; +// if i > l then Compare:=l1-l2; + Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, SearchRegExp, False); + end; +end; + +function TRegExpCollection.Find(ARegExp:shortstring;var P: PpcRegExp):boolean; +var I : integer; +begin + CompareModeInsert:=false; + SearchRegExp:=ARegExp; + if Search(nil,I) then + begin + P:=PpcRegExp(At(I)); + Find:=true; + end + else + begin + P:=nil; + Find:=false; + end; + CompareModeInsert:=true; +end; + +function TRegExpCollection.CheckNew(ARegExp:shortstring):PpcRegExp; +var + P : PpcRegExp; +begin + if not Find(ARegExp,P) then + begin + if Count = MaxRegExp then + AtFree(0); + P:=New(ppcRegExp,Init(ARegExp,PCRE_CASELESS,nil)); + Insert(P); + end; + CheckNew:=P; +end; + +function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean; +var + PpcRE:PpcRegExp; +begin + PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale)); + pcGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr)); + Dispose(PpcRE,Done); +end; + +function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string; +var + PpcRE:PpcRegExp; +begin + PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale)); + if PpcRE^.Search(pchar(AStr),Length(AStr)) then + pcGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl) + else + pcGrepSub:=''; + Dispose(PpcRE,Done); +end; + +function pcFastGrepMatch(WildCard, aStr: string): Boolean; +var + PpcRE:PpcRegExp; +begin + PpcRE:=PRegExpCache^.CheckNew(WildCard); + pcFastGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr)); +end; + +function pcFastGrepSub(WildCard, aStr, aRepl: string): string; +var + PpcRE:PpcRegExp; +begin + PpcRE:=PRegExpCache^.CheckNew(WildCard); + if PpcRE^.Search(pchar(AStr),Length(AStr)) then + pcFastGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl) + else + pcFastGrepSub:=''; +end; + +{$IFDEF PCRE_5_0} +function pcGetVersion : pchar; assembler; {$FRAME-}{$USES none} +asm + call pcre_version +end; +{$ENDIF PCRE_5_0} + +function pcError; +var P: ppcRegExp absolute pRegExp; +begin + Result := (P = nil) or P^.Error; + If Result and (P <> nil) then + begin +{ if P^.ErrorPos = 0 then + MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"', nil,mfConfirmation+mfOkButton) + else} + MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"'+GetString(erRegExpCompPos), + @P^.ErrorPos,mfConfirmation+mfOkButton); + Dispose(P, Done); + P:=nil; + end; +end; + +function pcInit; +var Options : Integer; +begin + If CaseSens then Options := 0 else Options := PCRE_CASELESS; + Result := New( PpcRegExp, Init( Pattern, + {DefaultOptions} + startup.MiscMultiData.cfgRegEx.DefaultOptions or Options, + DefaultLocaleTable) ); +end; + +Initialization + PRegExpCache:=New(PRegExpCollection,Init(64)); +Finalization + Dispose(PRegExpCache,Done); +End. Modified: freeswitch/trunk/libs/pcre/pcregrep.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcregrep.c (original) +++ freeswitch/trunk/libs/pcre/pcregrep.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ its pattern matching. On a Unix or Win32 system it can recurse into directories. - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -37,6 +37,10 @@ ----------------------------------------------------------------------------- */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <ctype.h> #include <locale.h> #include <stdio.h> @@ -46,9 +50,19 @@ #include <sys/types.h> #include <sys/stat.h> + +#ifdef HAVE_UNISTD_H #include <unistd.h> +#endif + +#ifdef SUPPORT_LIBZ +#include <zlib.h> +#endif + +#ifdef SUPPORT_LIBBZ2 +#include <bzlib.h> +#endif -#include "config.h" #include "pcre.h" #define FALSE 0 @@ -56,8 +70,8 @@ typedef int BOOL; -#define VERSION "4.3 01-Jun-2006" #define MAX_PATTERN_COUNT 100 +#define OFFSET_SIZE 99 #if BUFSIZ > 8192 #define MBUFTHIRD BUFSIZ @@ -65,13 +79,16 @@ #define MBUFTHIRD 8192 #endif - /* Values for the "filenames" variable, which specifies options for file name output. The order is important; it is assumed that a file name is wanted for all values greater than FN_DEFAULT. */ enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; +/* File reading styles */ + +enum { FR_PLAIN, FR_LIBZ, FR_LIBBZ2 }; + /* Actions for the -d and -D options */ enum { dee_READ, dee_SKIP, dee_RECURSE }; @@ -83,6 +100,10 @@ #define PO_LINE_MATCH 0x0002 #define PO_FIXED_STRINGS 0x0004 +/* Line ending types */ + +enum { EL_LF, EL_CR, EL_CRLF, EL_ANY, EL_ANYCRLF }; + /************************************************* @@ -100,8 +121,7 @@ static const char *jfriedl_postfix = ""; #endif -static int endlinebyte = '\n'; /* Last byte of endline sequence */ -static int endlineextra = 0; /* Extra bytes for endline sequence */ +static int endlinetype; static char *colour_string = (char *)"1;31"; static char *colour_option = NULL; @@ -115,14 +135,18 @@ static const unsigned char *pcretables = NULL; static int pattern_count = 0; -static pcre **pattern_list; -static pcre_extra **hints_list; +static pcre **pattern_list = NULL; +static pcre_extra **hints_list = NULL; static char *include_pattern = NULL; static char *exclude_pattern = NULL; +static char *include_dir_pattern = NULL; +static char *exclude_dir_pattern = NULL; static pcre *include_compiled = NULL; static pcre *exclude_compiled = NULL; +static pcre *include_dir_compiled = NULL; +static pcre *exclude_dir_compiled = NULL; static int after_context = 0; static int before_context = 0; @@ -135,13 +159,16 @@ static BOOL count_only = FALSE; static BOOL do_colour = FALSE; +static BOOL file_offsets = FALSE; static BOOL hyphenpending = FALSE; static BOOL invert = FALSE; +static BOOL line_offsets = FALSE; static BOOL multiline = FALSE; static BOOL number = FALSE; static BOOL only_matching = FALSE; static BOOL quiet = FALSE; static BOOL silent = FALSE; +static BOOL utf8 = FALSE; /* Structure for options and list of them */ @@ -159,13 +186,17 @@ /* Options without a single-letter equivalent get a negative value. This can be used to identify them. */ -#define N_COLOUR (-1) -#define N_EXCLUDE (-2) -#define N_HELP (-3) -#define N_INCLUDE (-4) -#define N_LABEL (-5) -#define N_LOCALE (-6) -#define N_NULL (-7) +#define N_COLOUR (-1) +#define N_EXCLUDE (-2) +#define N_EXCLUDE_DIR (-3) +#define N_HELP (-4) +#define N_INCLUDE (-5) +#define N_INCLUDE_DIR (-6) +#define N_LABEL (-7) +#define N_LOCALE (-8) +#define N_NULL (-9) +#define N_LOFFSETS (-10) +#define N_FOFFSETS (-11) static option_item optionlist[] = { { OP_NODATA, N_NULL, NULL, "", " terminate options" }, @@ -181,21 +212,25 @@ { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, + { OP_NODATA, N_FOFFSETS, NULL, "file-offsets", "output file offsets, not text" }, { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, + { OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" }, { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, - { OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LR, CRLF)" }, + { OP_STRING, 'N', &newline, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, { OP_STRING, N_EXCLUDE,&exclude_pattern, "exclude=pattern","exclude matching files when recursing" }, { OP_STRING, N_INCLUDE,&include_pattern, "include=pattern","include matching files when recursing" }, + { OP_STRING, N_EXCLUDE_DIR,&exclude_dir_pattern, "exclude_dir=pattern","exclude matching directories when recursing" }, + { OP_STRING, N_INCLUDE_DIR,&include_dir_pattern, "include_dir=pattern","include matching directories when recursing" }, #ifdef JFRIEDL_DEBUG { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, #endif @@ -219,6 +254,16 @@ static const char *suffix[] = { "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; +/* UTF-8 tables - used only when the newline setting is "any". */ + +const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; + +const char utf8_table4[] = { + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, + 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; + /************************************************* @@ -231,7 +276,7 @@ /************* Directory scanning in Unix ***********/ -#if IS_UNIX +#if defined HAVE_SYS_STAT_H && defined HAVE_DIRENT_H && defined HAVE_SYS_TYPES_H #include <sys/types.h> #include <sys/stat.h> #include <dirent.h> @@ -263,7 +308,7 @@ if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) return dent->d_name; } -return NULL; /* Keep compiler happy; never executed */ +/* Control never reaches here */ } static void @@ -298,10 +343,11 @@ /* I (Philip Hazel) have no means of testing this code. It was contributed by Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES -when it did not exist. */ - +when it did not exist. David Byron added a patch that moved the #include of +<windows.h> to before the INVALID_FILE_ATTRIBUTES definition rather than after. +*/ -#elif HAVE_WIN32API +#elif HAVE_WINDOWS_H #ifndef STRICT # define STRICT @@ -309,12 +355,13 @@ #ifndef WIN32_LEAN_AND_MEAN # define WIN32_LEAN_AND_MEAN #endif + +#include <windows.h> + #ifndef INVALID_FILE_ATTRIBUTES #define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF #endif -#include <windows.h> - typedef struct directory_type { HANDLE handle; @@ -399,7 +446,7 @@ int isregfile(char *filename) { -return !isdirectory(filename) +return !isdirectory(filename); } @@ -410,7 +457,7 @@ static BOOL is_stdout_tty(void) { -FALSE; +return FALSE; } @@ -423,8 +470,8 @@ typedef void directory_type; int isdirectory(char *filename) { return 0; } -directory_type * opendirectory(char *filename) {} -char *readdirectory(directory_type *dir) {} +directory_type * opendirectory(char *filename) { return (directory_type*)0;} +char *readdirectory(directory_type *dir) { return (char*)0;} void closedirectory(directory_type *dir) {} @@ -448,7 +495,7 @@ -#if ! HAVE_STRERROR +#ifndef HAVE_STRERROR /************************************************* * Provide strerror() for non-ANSI libraries * *************************************************/ @@ -471,6 +518,271 @@ /************************************************* +* Find end of line * +*************************************************/ + +/* The length of the endline sequence that is found is set via lenptr. This may +be zero at the very end of the file if there is no line-ending sequence there. + +Arguments: + p current position in line + endptr end of available data + lenptr where to put the length of the eol sequence + +Returns: pointer to the last byte of the line +*/ + +static char * +end_of_line(char *p, char *endptr, int *lenptr) +{ +switch(endlinetype) + { + default: /* Just in case */ + case EL_LF: + while (p < endptr && *p != '\n') p++; + if (p < endptr) + { + *lenptr = 1; + return p + 1; + } + *lenptr = 0; + return endptr; + + case EL_CR: + while (p < endptr && *p != '\r') p++; + if (p < endptr) + { + *lenptr = 1; + return p + 1; + } + *lenptr = 0; + return endptr; + + case EL_CRLF: + for (;;) + { + while (p < endptr && *p != '\r') p++; + if (++p >= endptr) + { + *lenptr = 0; + return endptr; + } + if (*p == '\n') + { + *lenptr = 2; + return p + 1; + } + } + break; + + case EL_ANYCRLF: + while (p < endptr) + { + int extra = 0; + register int c = *((unsigned char *)p); + + if (utf8 && c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (p[gcii] & 0x3f) << gcss; + } + } + + p += 1 + extra; + + switch (c) + { + case 0x0a: /* LF */ + *lenptr = 1; + return p; + + case 0x0d: /* CR */ + if (p < endptr && *p == 0x0a) + { + *lenptr = 2; + p++; + } + else *lenptr = 1; + return p; + + default: + break; + } + } /* End of loop for ANYCRLF case */ + + *lenptr = 0; /* Must have hit the end */ + return endptr; + + case EL_ANY: + while (p < endptr) + { + int extra = 0; + register int c = *((unsigned char *)p); + + if (utf8 && c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (p[gcii] & 0x3f) << gcss; + } + } + + p += 1 + extra; + + switch (c) + { + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + *lenptr = 1; + return p; + + case 0x0d: /* CR */ + if (p < endptr && *p == 0x0a) + { + *lenptr = 2; + p++; + } + else *lenptr = 1; + return p; + + case 0x85: /* NEL */ + *lenptr = utf8? 2 : 1; + return p; + + case 0x2028: /* LS */ + case 0x2029: /* PS */ + *lenptr = 3; + return p; + + default: + break; + } + } /* End of loop for ANY case */ + + *lenptr = 0; /* Must have hit the end */ + return endptr; + } /* End of overall switch */ +} + + + +/************************************************* +* Find start of previous line * +*************************************************/ + +/* This is called when looking back for before lines to print. + +Arguments: + p start of the subsequent line + startptr start of available data + +Returns: pointer to the start of the previous line +*/ + +static char * +previous_line(char *p, char *startptr) +{ +switch(endlinetype) + { + default: /* Just in case */ + case EL_LF: + p--; + while (p > startptr && p[-1] != '\n') p--; + return p; + + case EL_CR: + p--; + while (p > startptr && p[-1] != '\n') p--; + return p; + + case EL_CRLF: + for (;;) + { + p -= 2; + while (p > startptr && p[-1] != '\n') p--; + if (p <= startptr + 1 || p[-2] == '\r') return p; + } + return p; /* But control should never get here */ + + case EL_ANY: + case EL_ANYCRLF: + if (*(--p) == '\n' && p > startptr && p[-1] == '\r') p--; + if (utf8) while ((*p & 0xc0) == 0x80) p--; + + while (p > startptr) + { + register int c; + char *pp = p - 1; + + if (utf8) + { + int extra = 0; + while ((*pp & 0xc0) == 0x80) pp--; + c = *((unsigned char *)pp); + if (c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (pp[gcii] & 0x3f) << gcss; + } + } + } + else c = *((unsigned char *)pp); + + if (endlinetype == EL_ANYCRLF) switch (c) + { + case 0x0a: /* LF */ + case 0x0d: /* CR */ + return p; + + default: + break; + } + + else switch (c) + { + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LS */ + case 0x2029: /* PS */ + return p; + + default: + break; + } + + p = pp; /* Back one character */ + } /* End of loop for ANY case */ + + return startptr; /* Hit start of data */ + } /* End of overall switch */ +} + + + + + +/************************************************* * Print the previous "after" lines * *************************************************/ @@ -495,13 +807,13 @@ int count = 0; while (lastmatchrestart < endptr && count++ < after_context) { + int ellength; char *pp = lastmatchrestart; if (printname != NULL) fprintf(stdout, "%s-", printname); if (number) fprintf(stdout, "%d-", lastmatchnumber++); - while (*pp != endlinebyte) pp++; - fwrite(lastmatchrestart, 1, pp - lastmatchrestart + (1 + endlineextra), - stdout); - lastmatchrestart = pp + 1; + pp = end_of_line(pp, endptr, &ellength); + fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); + lastmatchrestart = pp; } hyphenpending = TRUE; } @@ -510,6 +822,60 @@ /************************************************* +* Apply patterns to subject till one matches * +*************************************************/ + +/* This function is called to run through all patterns, looking for a match. It +is used multiple times for the same subject when colouring is enabled, in order +to find all possible matches. + +Arguments: + matchptr the start of the subject + length the length of the subject to match + offsets the offets vector to fill in + mrc address of where to put the result of pcre_exec() + +Returns: TRUE if there was a match + FALSE if there was no match + invert if there was a non-fatal error +*/ + +static BOOL +match_patterns(char *matchptr, size_t length, int *offsets, int *mrc) +{ +int i; +for (i = 0; i < pattern_count; i++) + { + *mrc = pcre_exec(pattern_list[i], hints_list[i], matchptr, length, 0, + PCRE_NOTEMPTY, offsets, OFFSET_SIZE); + if (*mrc >= 0) return TRUE; + if (*mrc == PCRE_ERROR_NOMATCH) continue; + fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", *mrc); + if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); + fprintf(stderr, "this text:\n"); + fwrite(matchptr, 1, length, stderr); /* In case binary zero included */ + fprintf(stderr, "\n"); + if (error_count == 0 && + (*mrc == PCRE_ERROR_MATCHLIMIT || *mrc == PCRE_ERROR_RECURSIONLIMIT)) + { + fprintf(stderr, "pcregrep: error %d means that a resource limit " + "was exceeded\n", *mrc); + fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); + } + if (error_count++ > 20) + { + fprintf(stderr, "pcregrep: too many errors - abandoned\n"); + exit(2); + } + return invert; /* No more matching; don't show the line again */ + } + +return FALSE; /* No match, no errors */ +} + + + +/************************************************* * Grep an individual file * *************************************************/ @@ -521,34 +887,74 @@ "before" context printing. Arguments: - in the fopened FILE stream + handle the fopened FILE stream for a normal file + the gzFile pointer when reading is via libz + the BZFILE pointer when reading is via libbz2 + frtype FR_PLAIN, FR_LIBZ, or FR_LIBBZ2 printname the file name if it is to be printed for each match or NULL if the file name is not to be printed it cannot be NULL if filenames[_nomatch]_only is set Returns: 0 if there was at least one match 1 otherwise (no matches) + 2 if there is a read error on a .bz2 file */ static int -pcregrep(FILE *in, char *printname) +pcregrep(void *handle, int frtype, char *printname) { int rc = 1; int linenumber = 1; int lastmatchnumber = 0; int count = 0; -int offsets[99]; +int filepos = 0; +int offsets[OFFSET_SIZE]; char *lastmatchrestart = NULL; char buffer[3*MBUFTHIRD]; char *ptr = buffer; char *endptr; size_t bufflength; BOOL endhyphenpending = FALSE; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif + + +/* Do the first read into the start of the buffer and set up the pointer to end +of what we have. In the case of libz, a non-zipped .gz file will be read as a +plain file. However, if a .bz2 file isn't actually bzipped, the first read will +fail. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + { + ingz = (gzFile)handle; + bufflength = gzread (ingz, buffer, 3*MBUFTHIRD); + } +else +#endif -/* Do the first read into the start of the buffer and set up the pointer to -end of what we have. */ +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + inbz2 = (BZFILE *)handle; + bufflength = BZ2_bzread(inbz2, buffer, 3*MBUFTHIRD); + if ((int)bufflength < 0) return 2; /* Gotcha: bufflength is size_t; */ + } /* without the cast it is unsigned. */ +else +#endif + + { + in = (FILE *)handle; + bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); + } -bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); endptr = buffer + bufflength; /* Loop while the current pointer is not at the end of the file. For large @@ -558,23 +964,24 @@ while (ptr < endptr) { - int i; + int endlinelength; int mrc = 0; - BOOL match = FALSE; + BOOL match; + char *matchptr = ptr; char *t = ptr; size_t length, linelength; /* At this point, ptr is at the start of a line. We need to find the length of the subject string to pass to pcre_exec(). In multiline mode, it is the length remainder of the data in the buffer. Otherwise, it is the length of - the next line. After matching, we always advance by the length of the next - line. In multiline mode the PCRE_FIRSTLINE option is used for compiling, so - that any match is constrained to be in the first line. */ - - linelength = 0; - while (t < endptr && *t++ != endlinebyte) linelength++; - length = multiline? endptr - ptr : linelength; - + the next line, excluding the terminating newline. After matching, we always + advance by the length of the next line. In multiline mode the PCRE_FIRSTLINE + option is used for compiling, so that any match is constrained to be in the + first line. */ + + t = end_of_line(t, endptr, &endlinelength); + linelength = t - ptr - endlinelength; + length = multiline? (size_t)(endptr - ptr) : linelength; /* Extra processing for Jeffrey Friedl's debugging. */ @@ -585,6 +992,7 @@ #include <time.h> struct timeval start_time, end_time; struct timezone dummy; + int i; if (jfriedl_XT) { @@ -610,7 +1018,8 @@ for (i = 0; i < jfriedl_XR; i++) - match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, 0, offsets, 99) >= 0); + match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, + PCRE_NOTEMPTY, offsets, OFFSET_SIZE) >= 0); if (gettimeofday(&end_time, &dummy) != 0) perror("bad gettimeofday"); @@ -624,38 +1033,16 @@ } #endif + /* We come back here after a match when the -o option (only_matching) is set, + in order to find any further matches in the same line. */ - /* Run through all the patterns until one matches. Note that we don't include - the final newline in the subject string. */ + ONLY_MATCHING_RESTART: - for (i = 0; i < pattern_count; i++) - { - mrc = pcre_exec(pattern_list[i], hints_list[i], ptr, length, 0, 0, - offsets, 99); - if (mrc >= 0) { match = TRUE; break; } - if (mrc != PCRE_ERROR_NOMATCH) - { - fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", mrc); - if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); - fprintf(stderr, "this line:\n"); - fwrite(ptr, 1, linelength, stderr); /* In case binary zero included */ - fprintf(stderr, "\n"); - if (error_count == 0 && - (mrc == PCRE_ERROR_MATCHLIMIT || mrc == PCRE_ERROR_RECURSIONLIMIT)) - { - fprintf(stderr, "pcregrep: error %d means that a resource limit " - "was exceeded\n", mrc); - fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); - } - if (error_count++ > 20) - { - fprintf(stderr, "pcregrep: too many errors - abandoned\n"); - exit(2); - } - match = invert; /* No more matching; don't show the line again */ - break; - } - } + /* Run through all the patterns until one matches or there is an error other + than NOMATCH. This code is in a subroutine so that it can be re-used for + finding subsequent matches when colouring matched lines. */ + + match = match_patterns(matchptr, length, offsets, &mrc); /* If it's a match or a not-match (as required), do what's wanted. */ @@ -685,14 +1072,37 @@ else if (quiet) return 0; /* The --only-matching option prints just the substring that matched, and - does not pring any context. */ + the --file-offsets and --line-offsets options output offsets for the + matching substring (they both force --only-matching). None of these options + prints any context. Afterwards, adjust the start and length, and then jump + back to look for further matches in the same line. If we are in invert + mode, however, nothing is printed - this could be still useful because the + return code is set. */ else if (only_matching) { - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "\n"); + if (!invert) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + if (line_offsets) + fprintf(stdout, "%d,%d", (int)(matchptr + offsets[0] - ptr), + offsets[1] - offsets[0]); + else if (file_offsets) + fprintf(stdout, "%d,%d", (int)(filepos + matchptr + offsets[0] - ptr), + offsets[1] - offsets[0]); + else + { + if (do_colour) fprintf(stdout, "%c[%sm", 0x1b, colour_string); + fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + if (do_colour) fprintf(stdout, "%c[00m", 0x1b); + } + fprintf(stdout, "\n"); + matchptr += offsets[1]; + length -= offsets[1]; + match = FALSE; + goto ONLY_MATCHING_RESTART; + } } /* This is the default case when none of the above options is set. We print @@ -706,13 +1116,13 @@ if (after_context > 0 && lastmatchnumber > 0) { + int ellength; int linecount = 0; char *p = lastmatchrestart; while (p < ptr && linecount < after_context) { - while (*p != endlinebyte) p++; - p++; + p = end_of_line(p, ptr, &ellength); linecount++; } @@ -725,10 +1135,9 @@ char *pp = lastmatchrestart; if (printname != NULL) fprintf(stdout, "%s-", printname); if (number) fprintf(stdout, "%d-", lastmatchnumber++); - while (*pp != endlinebyte) pp++; - fwrite(lastmatchrestart, 1, pp - lastmatchrestart + - (1 + endlineextra), stdout); - lastmatchrestart = pp + 1; + pp = end_of_line(pp, endptr, &ellength); + fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); + lastmatchrestart = pp; } if (lastmatchrestart != ptr) hyphenpending = TRUE; } @@ -754,8 +1163,7 @@ linecount < before_context) { linecount++; - p--; - while (p > buffer && p[-1] != endlinebyte) p--; + p = previous_line(p, buffer); } if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) @@ -763,12 +1171,13 @@ while (p < ptr) { + int ellength; char *pp = p; if (printname != NULL) fprintf(stdout, "%s-", printname); if (number) fprintf(stdout, "%d-", linenumber - linecount--); - while (*pp != endlinebyte) pp++; - fwrite(p, 1, pp - p + (1 + endlineextra), stdout); - p = pp + 1; + pp = end_of_line(pp, endptr, &ellength); + fwrite(p, 1, pp - p, stdout); + p = pp; } } @@ -783,16 +1192,26 @@ /* In multiline mode, we want to print to the end of the line in which the end of the matched string is found, so we adjust linelength and the - line number appropriately. Because the PCRE_FIRSTLINE option is set, the - start of the match will always be before the first newline sequence. */ + line number appropriately, but only when there actually was a match + (invert not set). Because the PCRE_FIRSTLINE option is set, the start of + the match will always be before the first newline sequence. */ if (multiline) { - char *endmatch = ptr + offsets[1]; - t = ptr; - while (t < endmatch) { if (*t++ == endlinebyte) linenumber++; } - while (endmatch < endptr && *endmatch != endlinebyte) endmatch++; - linelength = endmatch - ptr; + int ellength; + char *endmatch = ptr; + if (!invert) + { + endmatch += offsets[1]; + t = ptr; + while (t < endmatch) + { + t = end_of_line(t, endptr, &ellength); + if (t <= endmatch) linenumber++; else break; + } + } + endmatch = end_of_line(endmatch, endptr, &ellength); + linelength = endmatch - ptr - ellength; } /*** NOTE: Use only fwrite() to output the data line, so that binary @@ -814,19 +1233,34 @@ else #endif - /* We have to split the line(s) up if colouring. */ + /* We have to split the line(s) up if colouring, and search for further + matches. */ if (do_colour) { + int last_offset = 0; fwrite(ptr, 1, offsets[0], stdout); fprintf(stdout, "%c[%sm", 0x1b, colour_string); fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); fprintf(stdout, "%c[00m", 0x1b); - fwrite(ptr + offsets[1], 1, linelength - offsets[1], stdout); + for (;;) + { + last_offset += offsets[1]; + matchptr += offsets[1]; + length -= offsets[1]; + if (!match_patterns(matchptr, length, offsets, &mrc)) break; + fwrite(matchptr, 1, offsets[0], stdout); + fprintf(stdout, "%c[%sm", 0x1b, colour_string); + fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "%c[00m", 0x1b); + } + fwrite(ptr + last_offset, 1, (linelength + endlinelength) - last_offset, + stdout); } - else fwrite(ptr, 1, linelength, stdout); - fprintf(stdout, "\n"); + /* Not colouring; no need to search for further matches */ + + else fwrite(ptr, 1, linelength + endlinelength, stdout); } /* End of doing what has to be done for a match */ @@ -836,13 +1270,33 @@ /* Remember where the last match happened for after_context. We remember where we are about to restart, and that line's number. */ - lastmatchrestart = ptr + linelength + 1; + lastmatchrestart = ptr + linelength + endlinelength; lastmatchnumber = linenumber + 1; } - /* Advance to after the newline and increment the line number. */ + /* For a match in multiline inverted mode (which of course did not cause + anything to be printed), we have to move on to the end of the match before + proceeding. */ + + if (multiline && invert && match) + { + int ellength; + char *endmatch = ptr + offsets[1]; + t = ptr; + while (t < endmatch) + { + t = end_of_line(t, endptr, &ellength); + if (t <= endmatch) linenumber++; else break; + } + endmatch = end_of_line(endmatch, endptr, &ellength); + linelength = endmatch - ptr - ellength; + } - ptr += linelength + 1; + /* Advance to after the newline and increment the line number. The file + offset to the current line is maintained in filepos. */ + + ptr += linelength + endlinelength; + filepos += linelength + endlinelength; linenumber++; /* If we haven't yet reached the end of the file (the buffer is full), and @@ -864,7 +1318,23 @@ memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); ptr -= MBUFTHIRD; + +#ifdef SUPPORT_LIBZ + if (frtype == FR_LIBZ) + bufflength = 2*MBUFTHIRD + + gzread (ingz, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + +#ifdef SUPPORT_LIBBZ2 + if (frtype == FR_LIBBZ2) + bufflength = 2*MBUFTHIRD + + BZ2_bzread(inbz2, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); + endptr = buffer + bufflength; /* Adjust any last match point */ @@ -928,21 +1398,32 @@ { int rc = 1; int sep; -FILE *in; +int frtype; +int pathlen; +void *handle; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif /* If the file name is "-" we scan stdin */ if (strcmp(pathname, "-") == 0) { - return pcregrep(stdin, + return pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? stdin_name : NULL); } - /* If the file is a directory, skip if skipping or if we are recursing, scan -each file within it, subject to any include or exclude patterns that were set. -The scanning code is localized so it can be made system-specific. */ +each file and directory within it, subject to any include or exclude patterns +that were set. The scanning code is localized so it can be made +system-specific. */ if ((sep = isdirectory(pathname)) != 0) { @@ -963,17 +1444,30 @@ while ((nextfile = readdirectory(dir)) != NULL) { - int frc, blen; + int frc, nflen; sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile); - blen = strlen(buffer); + nflen = strlen(nextfile); + + if (isdirectory(buffer)) + { + if (exclude_dir_compiled != NULL && + pcre_exec(exclude_dir_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) >= 0) + continue; + + if (include_dir_compiled != NULL && + pcre_exec(include_dir_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) < 0) + continue; + } + else + { + if (exclude_compiled != NULL && + pcre_exec(exclude_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) >= 0) + continue; - if (exclude_compiled != NULL && - pcre_exec(exclude_compiled, NULL, buffer, blen, 0, 0, NULL, 0) >= 0) - continue; - - if (include_compiled != NULL && - pcre_exec(include_compiled, NULL, buffer, blen, 0, 0, NULL, 0) < 0) - continue; + if (include_compiled != NULL && + pcre_exec(include_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) < 0) + continue; + } frc = grep_or_recurse(buffer, dir_recurse, FALSE); if (frc > 1) rc = frc; @@ -996,8 +1490,54 @@ argument at top level, we don't show the file name, unless we are only showing the file name, or the filename was forced (-H). */ -in = fopen(pathname, "r"); -if (in == NULL) +pathlen = strlen(pathname); + +/* Open using zlib if it is supported and the file name ends with .gz. */ + +#ifdef SUPPORT_LIBZ +if (pathlen > 3 && strcmp(pathname + pathlen - 3, ".gz") == 0) + { + ingz = gzopen(pathname, "rb"); + if (ingz == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, + strerror(errno)); + return 2; + } + handle = (void *)ingz; + frtype = FR_LIBZ; + } +else +#endif + +/* Otherwise open with bz2lib if it is supported and the name ends with .bz2. */ + +#ifdef SUPPORT_LIBBZ2 +if (pathlen > 4 && strcmp(pathname + pathlen - 4, ".bz2") == 0) + { + inbz2 = BZ2_bzopen(pathname, "rb"); + handle = (void *)inbz2; + frtype = FR_LIBBZ2; + } +else +#endif + +/* Otherwise use plain fopen(). The label is so that we can come back here if +an attempt to read a .bz2 file indicates that it really is a plain file. */ + +#ifdef SUPPORT_LIBBZ2 +PLAIN_FILE: +#endif + { + in = fopen(pathname, "r"); + handle = (void *)in; + frtype = FR_PLAIN; + } + +/* All the opening methods return errno when they fail. */ + +if (handle == NULL) { if (!silent) fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, @@ -1005,10 +1545,50 @@ return 2; } -rc = pcregrep(in, (filenames > FN_DEFAULT || +/* Now grep the file */ + +rc = pcregrep(handle, frtype, (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); +/* Close in an appropriate manner. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + gzclose(ingz); +else +#endif + +/* If it is a .bz2 file and the result is 2, it means that the first attempt to +read failed. If the error indicates that the file isn't in fact bzipped, try +again as a normal file. */ + +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + if (rc == 2) + { + int errnum; + const char *err = BZ2_bzerror(inbz2, &errnum); + if (errnum == BZ_DATA_ERROR_MAGIC) + { + BZ2_bzclose(inbz2); + goto PLAIN_FILE; + } + else if (!silent) + fprintf(stderr, "pcregrep: Failed to read %s using bzlib: %s\n", + pathname, err); + } + BZ2_bzclose(inbz2); + } +else +#endif + +/* Normal file close */ + fclose(in); + +/* Pass back the yield from pcregrep(). */ + return rc; } @@ -1029,7 +1609,8 @@ if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); } fprintf(stderr, "] [long options] [pattern] [files]\n"); -fprintf(stderr, "Type `pcregrep --help' for more information.\n"); +fprintf(stderr, "Type `pcregrep --help' for more information and the long " + "options.\n"); return rc; } @@ -1048,9 +1629,23 @@ printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); printf("Search for PATTERN in each FILE or standard input.\n"); printf("PATTERN must be present if neither -e nor -f is used.\n"); -printf("\"-\" can be used as a file name to mean STDIN.\n\n"); -printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); +printf("\"-\" can be used as a file name to mean STDIN.\n"); +#ifdef SUPPORT_LIBZ +printf("Files whose names end in .gz are read using zlib.\n"); +#endif + +#ifdef SUPPORT_LIBBZ2 +printf("Files whose names end in .bz2 are read using bzlib2.\n"); +#endif + +#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 +printf("Other files and the standard input are read as plain files.\n\n"); +#else +printf("All files are read as plain files, without any interpretation.\n\n"); +#endif + +printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); printf("Options:\n"); for (op = optionlist; op->one_char != 0; op++) @@ -1058,8 +1653,7 @@ int n; char s[4]; if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); - printf(" %s --%s%n", s, op->long_name, &n); - n = 30 - n; + n = 30 - printf(" %s --%s", s, op->long_name); if (n < 1) n = 1; printf("%.*s%s\n", n, " ", op->help_text); } @@ -1084,7 +1678,9 @@ { switch(letter) { + case N_FOFFSETS: file_offsets = TRUE; break; case N_HELP: help(); exit(0); + case N_LOFFSETS: line_offsets = number = TRUE; break; case 'c': count_only = TRUE; break; case 'F': process_options |= PO_FIXED_STRINGS; break; case 'H': filenames = FN_FORCE; break; @@ -1098,14 +1694,13 @@ case 'q': quiet = TRUE; break; case 'r': dee_action = dee_RECURSE; break; case 's': silent = TRUE; break; - case 'u': options |= PCRE_UTF8; break; + case 'u': options |= PCRE_UTF8; utf8 = TRUE; break; case 'v': invert = TRUE; break; case 'w': process_options |= PO_WORD_MATCH; break; case 'x': process_options |= PO_LINE_MATCH; break; case 'V': - fprintf(stderr, "pcregrep version %s using ", VERSION); - fprintf(stderr, "PCRE version %s\n", pcre_version()); + fprintf(stderr, "pcregrep version %s\n", pcre_version()); exit(0); break; @@ -1181,7 +1776,11 @@ suffix[process_options]); pattern_list[pattern_count] = pcre_compile(buffer, options, &error, &errptr, pcretables); -if (pattern_list[pattern_count++] != NULL) return TRUE; +if (pattern_list[pattern_count] != NULL) + { + pattern_count++; + return TRUE; + } /* Handle compile errors */ @@ -1231,14 +1830,16 @@ { if ((process_options & PO_FIXED_STRINGS) != 0) { + char *eop = pattern + strlen(pattern); char buffer[MBUFTHIRD]; for(;;) { - char *p = strchr(pattern, endlinebyte); - if (p == NULL) + int ellength; + char *p = end_of_line(pattern, eop, &ellength); + if (ellength == 0) return compile_single_pattern(pattern, options, filename, count); - sprintf(buffer, "%.*s", p - pattern - endlineextra, pattern); - pattern = p + 1; + sprintf(buffer, "%.*s", (int)(p - pattern - ellength), pattern); + pattern = p; if (!compile_single_pattern(buffer, options, filename, count)) return FALSE; } @@ -1261,20 +1862,27 @@ int rc = 1; int pcre_options = 0; int cmd_pattern_count = 0; +int hint_count = 0; int errptr; BOOL only_one_at_top; char *patterns[MAX_PATTERN_COUNT]; const char *locale_from = "--locale"; const char *error; -/* Set the default line ending value from the default in the PCRE library. */ +/* Set the default line ending value from the default in the PCRE library; +"lf", "cr", "crlf", and "any" are supported. Anything else is treated as "lf". +Note that the return values from pcre_config(), though derived from the ASCII +codes, are the same in EBCDIC environments, so we must use the actual values +rather than escapes such as as '\r'. */ (void)pcre_config(PCRE_CONFIG_NEWLINE, &i); switch(i) { - default: newline = (char *)"lf"; break; - case '\r': newline = (char *)"cr"; break; - case ('\r' << 8) | '\n': newline = (char *)"crlf"; break; + default: newline = (char *)"lf"; break; + case 13: newline = (char *)"cr"; break; + case (13 << 8) | 10: newline = (char *)"crlf"; break; + case -1: newline = (char *)"any"; break; + case -2: newline = (char *)"anycrlf"; break; } /* Process the options */ @@ -1332,7 +1940,7 @@ else /* Special case xxx=data */ { int oplen = equals - op->long_name; - int arglen = (argequals == NULL)? strlen(arg) : argequals - arg; + int arglen = (argequals == NULL)? (int)strlen(arg) : argequals - arg; if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) { option_data = arg + arglen; @@ -1351,8 +1959,8 @@ char buff2[24]; int baselen = opbra - op->long_name; sprintf(buff1, "%.*s", baselen, op->long_name); - sprintf(buff2, "%s%.*s", buff1, strlen(op->long_name) - baselen - 2, - opbra + 1); + sprintf(buff2, "%s%.*s", buff1, + (int)strlen(op->long_name) - baselen - 2, opbra + 1); if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0) break; } @@ -1511,6 +2119,19 @@ if (before_context == 0) before_context = both_context; } +/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted. +However, the latter two set the only_matching flag. */ + +if ((only_matching && (file_offsets || line_offsets)) || + (file_offsets && line_offsets)) + { + fprintf(stderr, "pcregrep: Cannot mix --only-matching, --file-offsets " + "and/or --line-offsets\n"); + exit(usage(2)); + } + +if (file_offsets || line_offsets) only_matching = TRUE; + /* If a locale has not been provided as an option, see if the LC_CTYPE or LC_ALL environment variable is set, and if so, use it. */ @@ -1565,16 +2186,27 @@ if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) { pcre_options |= PCRE_NEWLINE_CR; - endlinebyte = '\r'; + endlinetype = EL_CR; } else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) { pcre_options |= PCRE_NEWLINE_LF; + endlinetype = EL_LF; } else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) { pcre_options |= PCRE_NEWLINE_CRLF; - endlineextra = 1; + endlinetype = EL_CRLF; + } +else if (strcmp(newline, "any") == 0 || strcmp(newline, "ANY") == 0) + { + pcre_options |= PCRE_NEWLINE_ANY; + endlinetype = EL_ANY; + } +else if (strcmp(newline, "anycrlf") == 0 || strcmp(newline, "ANYCRLF") == 0) + { + pcre_options |= PCRE_NEWLINE_ANYCRLF; + endlinetype = EL_ANYCRLF; } else { @@ -1630,7 +2262,7 @@ if (pattern_list == NULL || hints_list == NULL) { fprintf(stderr, "pcregrep: malloc failed\n"); - return 2; + goto EXIT2; } /* If no patterns were provided by -e, and there is no file provided by -f, @@ -1649,7 +2281,7 @@ { if (!compile_pattern(patterns[j], pcre_options, NULL, (j == 0 && cmd_pattern_count == 1)? 0 : j + 1)) - return 2; + goto EXIT2; } /* Compile the regular expressions that are provided in a file. */ @@ -1673,7 +2305,7 @@ { fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename, strerror(errno)); - return 2; + goto EXIT2; } filename = pattern_filename; } @@ -1686,7 +2318,7 @@ linenumber++; if (buffer[0] == 0) continue; /* Skip blank lines */ if (!compile_pattern(buffer, pcre_options, filename, linenumber)) - return 2; + goto EXIT2; } if (f != stdin) fclose(f); @@ -1702,8 +2334,9 @@ char s[16]; if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j); fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); - return 2; + goto EXIT2; } + hint_count++; } /* If there are include or exclude patterns, compile them. */ @@ -1716,7 +2349,7 @@ { fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n", errptr, error); - return 2; + goto EXIT2; } } @@ -1728,14 +2361,41 @@ { fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n", errptr, error); - return 2; + goto EXIT2; + } + } + +if (exclude_dir_pattern != NULL) + { + exclude_dir_compiled = pcre_compile(exclude_dir_pattern, 0, &error, &errptr, + pcretables); + if (exclude_dir_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'exclude_dir' regex at offset %d: %s\n", + errptr, error); + goto EXIT2; + } + } + +if (include_dir_pattern != NULL) + { + include_dir_compiled = pcre_compile(include_dir_pattern, 0, &error, &errptr, + pcretables); + if (include_dir_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'include_dir' regex at offset %d: %s\n", + errptr, error); + goto EXIT2; } } /* If there are no further arguments, do the business on stdin and exit. */ if (i >= argc) - return pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL); + { + rc = pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT)? stdin_name : NULL); + goto EXIT; + } /* Otherwise, work through the remaining arguments as files or directories. Pass in the fact that there is only one argument at top level - this suppresses @@ -1752,7 +2412,22 @@ else if (frc == 0 && rc == 1) rc = 0; } +EXIT: +if (pattern_list != NULL) + { + for (i = 0; i < pattern_count; i++) free(pattern_list[i]); + free(pattern_list); + } +if (hints_list != NULL) + { + for (i = 0; i < hint_count; i++) free(hints_list[i]); + free(hints_list); + } return rc; + +EXIT2: +rc = 2; +goto EXIT; } /* End of pcregrep */ Modified: freeswitch/trunk/libs/pcre/pcreposix.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcreposix.c (original) +++ freeswitch/trunk/libs/pcre/pcreposix.c Mon Jun 8 18:51:30 2009 @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -42,10 +42,24 @@ functions. */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + + +/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for +compiling these functions. This must come before including pcreposix.h, where +they are set for an application (using these functions) if they have not +previously been set. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# define PCREPOSIX_EXP_DECL extern __declspec(dllexport) +# define PCREPOSIX_EXP_DEFN __declspec(dllexport) +#endif + +#include "pcre.h" #include "pcre_internal.h" #include "pcreposix.h" -#include "stdlib.h" - /* Table to translate PCRE compile time error codes into POSIX error codes. */ @@ -78,9 +92,9 @@ REG_BADPAT, /* unrecognized character after (?< */ REG_BADPAT, /* lookbehind assertion is not fixed length */ REG_BADPAT, /* malformed number or name after (?( */ - REG_BADPAT, /* conditional group containe more than two branches */ + REG_BADPAT, /* conditional group contains more than two branches */ REG_BADPAT, /* assertion expected after (?( */ - REG_BADPAT, /* (?R or (?digits must be followed by ) */ + REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ REG_ECTYPE, /* unknown POSIX class name */ REG_BADPAT, /* POSIX collating elements are not supported */ REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ @@ -93,7 +107,7 @@ REG_BADPAT, /* closing ) for (?C expected */ REG_BADPAT, /* recursive call could loop indefinitely */ REG_BADPAT, /* unrecognized character after (?P */ - REG_BADPAT, /* syntax error after (?P */ + REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ REG_BADPAT, /* two named subpatterns have the same name */ REG_BADPAT, /* invalid UTF-8 string */ REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ @@ -102,7 +116,18 @@ REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ REG_BADPAT, /* repeated subpattern is too long */ - REG_BADPAT /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* internal error: overran compiling workspace */ + REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ + REG_BADPAT, /* DEFINE group contains more than one branch */ + REG_BADPAT, /* repeating a DEFINE group is not allowed */ + REG_INVARG, /* inconsistent NEWLINE options */ + REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ + REG_BADPAT, /* (?+ or (?- must be followed by a non-zero number */ + REG_BADPAT, /* number is too big */ + REG_BADPAT, /* subpattern name expected */ + REG_BADPAT, /* digit expected after (?+ */ + REG_BADPAT /* ] is an invalid data character in JavaScript compatibility mode */ }; /* Table of texts corresponding to POSIX error codes */ @@ -135,7 +160,7 @@ * Translate error code to string * *************************************************/ -PCRE_DATA_SCOPE size_t +PCREPOSIX_EXP_DEFN size_t PCRE_CALL_CONVENTION regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) { const char *message, *addmessage; @@ -170,7 +195,7 @@ * Free store held by a regex * *************************************************/ -PCRE_DATA_SCOPE void +PCREPOSIX_EXP_DEFN void PCRE_CALL_CONVENTION regfree(regex_t *preg) { (pcre_free)(preg->re_pcre); @@ -193,7 +218,7 @@ various non-zero codes on failure */ -PCRE_DATA_SCOPE int +PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION regcomp(regex_t *preg, const char *pattern, int cflags) { const char *errorptr; @@ -235,11 +260,11 @@ be set. When this is the case, the nmatch and pmatch arguments are ignored, and the only result is yes/no/error. */ -PCRE_DATA_SCOPE int +PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags) { -int rc; +int rc, so, eo; int options = 0; int *ovector = NULL; int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; @@ -249,6 +274,7 @@ if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; +if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY; ((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ @@ -272,7 +298,23 @@ } } -rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string), +/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings. +The man page from OS X says "REG_STARTEND affects only the location of the +string, not how it is matched". That is why the "so" value is used to bump the +start location rather than being passed as a PCRE "starting offset". */ + +if ((eflags & REG_STARTEND) != 0) + { + so = pmatch[0].rm_so; + eo = pmatch[0].rm_eo; + } +else + { + so = 0; + eo = strlen(string); + } + +rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string + so, (eo - so), 0, options, ovector, nmatch * 3); if (rc == 0) rc = nmatch; /* All captured slots were filled in */ Modified: freeswitch/trunk/libs/pcre/pcreposix.h ============================================================================== --- freeswitch/trunk/libs/pcre/pcreposix.h (original) +++ freeswitch/trunk/libs/pcre/pcreposix.h Mon Jun 8 18:51:30 2009 @@ -9,7 +9,7 @@ Compatible Regular Expression library. It defines the things POSIX says should be there. I hope. - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2009 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -59,6 +59,8 @@ #define REG_DOTALL 0x0010 /* NOT defined by POSIX. */ #define REG_NOSUB 0x0020 #define REG_UTF8 0x0040 /* NOT defined by POSIX. */ +#define REG_STARTEND 0x0080 /* BSD feature: pass subject string by so,eo */ +#define REG_NOTEMPTY 0x0100 /* NOT defined by POSIX. */ /* This is not used by PCRE, but by defining it we make it easier to slot PCRE into existing programs that make POSIX calls. */ @@ -105,40 +107,35 @@ regoff_t rm_eo; } regmatch_t; -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ - -#ifndef PCRE_DATA_SCOPE -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) -# endif -# endif -#endif +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export settings are needed, and are set in pcreposix.c before including this +file. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL) +# define PCREPOSIX_EXP_DECL extern __declspec(dllimport) +# define PCREPOSIX_EXP_DEFN __declspec(dllimport) #endif -/* Otherwise, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCREPOSIX_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCREPOSIX_EXP_DECL extern "C" +# define PCREPOSIX_EXP_DEFN extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCREPOSIX_EXP_DECL extern +# define PCREPOSIX_EXP_DEFN extern # endif #endif /* The functions */ -PCRE_DATA_SCOPE int regcomp(regex_t *, const char *, int); -PCRE_DATA_SCOPE int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); -PCRE_DATA_SCOPE size_t regerror(int, const regex_t *, char *, size_t); -PCRE_DATA_SCOPE void regfree(regex_t *); +PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int); +PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, + regmatch_t *, int); +PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); +PCREPOSIX_EXP_DECL void regfree(regex_t *); #ifdef __cplusplus } /* extern "C" */ Modified: freeswitch/trunk/libs/pcre/pcretest.c ============================================================================== --- freeswitch/trunk/libs/pcre/pcretest.c (original) +++ freeswitch/trunk/libs/pcre/pcretest.c Mon Jun 8 18:51:30 2009 @@ -36,6 +36,10 @@ */ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + #include <ctype.h> #include <stdio.h> #include <string.h> @@ -44,23 +48,62 @@ #include <locale.h> #include <errno.h> -#ifndef _WIN32 -#include <sys/resource.h> +#ifdef SUPPORT_LIBREADLINE +#ifdef HAVE_UNISTD_H +#include <unistd.h> +#endif +#include <readline/readline.h> +#include <readline/history.h> #endif -#define PCRE_SPY /* For Win32 build, import data, not export */ -/* We include pcre_internal.h because we need the internal info for displaying -the results of pcre_study() and we also need to know about the internal -macros, structures, and other internal data values; pcretest has "inside -information" compared to a program that strictly follows the PCRE API. */ +/* A number of things vary for Windows builds. Originally, pcretest opened its +input and output without "b"; then I was told that "b" was needed in some +environments, so it was added for release 5.0 to both the input and output. (It +makes no difference on Unix-like systems.) Later I was told that it is wrong +for the input on Windows. I've now abstracted the modes into two macros that +are set here, to make it easier to fiddle with them, and removed "b" from the +input mode under Windows. */ + +#if defined(_WIN32) || defined(WIN32) +#include <io.h> /* For _setmode() */ +#include <fcntl.h> /* For _O_BINARY */ +#define INPUT_MODE "r" +#define OUTPUT_MODE "wb" + +#ifndef isatty +#define isatty _isatty /* This is what Windows calls them, I'm told, */ +#endif /* though in some environments they seem to */ + /* be already defined, hence the #ifndefs. */ +#ifndef fileno +#define fileno _fileno +#endif + +#else +#include <sys/time.h> /* These two includes are needed */ +#include <sys/resource.h> /* for setrlimit(). */ +#define INPUT_MODE "rb" +#define OUTPUT_MODE "wb" +#endif + +/* We have to include pcre_internal.h because we need the internal info for +displaying the results of pcre_study() and we also need to know about the +internal macros, structures, and other internal data values; pcretest has +"inside information" compared to a program that strictly follows the PCRE API. + +Although pcre_internal.h does itself include pcre.h, we explicitly include it +here before pcre_internal.h so that the PCRE_EXP_xxx macros get set +appropriately for an application, not for building PCRE. */ + +#include "pcre.h" #include "pcre_internal.h" -/* We need access to the data tables that PCRE uses. So as not to have to keep -two copies, we include the source file here, changing the names of the external -symbols to prevent clashes. */ +/* We need access to some of the data tables that PCRE uses. So as not to have +to keep two copies, we include the source file here, changing the names of the +external symbols to prevent clashes. */ +#define _pcre_ucp_gentype ucp_gentype #define _pcre_utf8_table1 utf8_table1 #define _pcre_utf8_table1_size utf8_table1_size #define _pcre_utf8_table2 utf8_table2 @@ -68,16 +111,25 @@ #define _pcre_utf8_table4 utf8_table4 #define _pcre_utt utt #define _pcre_utt_size utt_size +#define _pcre_utt_names utt_names #define _pcre_OP_lengths OP_lengths #include "pcre_tables.c" /* We also need the pcre_printint() function for printing out compiled patterns. This function is in a separate file so that it can be included in -pcre_compile.c when that module is compiled with debugging enabled. */ +pcre_compile.c when that module is compiled with debugging enabled. + +The definition of the macro PRINTABLE, which determines whether to print an +output character as-is or as a hex value when showing compiled patterns, is +contained in this file. We uses it here also, in cases when the locale has not +been explicitly changed, so as to get consistent output from systems that +differ in their output from isprint() even in the "C" locale. */ #include "pcre_printint.src" +#define PRINTHEX(c) (locale_set? isprint(c) : PRINTABLE(c)) + /* It is possible to compile this test program without including support for testing the POSIX interface, though this is not available via the standard @@ -87,10 +139,17 @@ #include "pcreposix.h" #endif -/* It is also possible, for the benefit of the version imported into Exim, to -build pcretest without support for UTF8 (define NOUTF8), without the interface -to the DFA matcher (NODFA), and without the doublecheck of the old "info" -function (define NOINFOCHECK). */ +/* It is also possible, for the benefit of the version currently imported into +Exim, to build pcretest without support for UTF8 (define NOUTF8), without the +interface to the DFA matcher (NODFA), and without the doublecheck of the old +"info" function (define NOINFOCHECK). In fact, we automatically cut out the +UTF8 support if PCRE is built without it. */ + +#ifndef SUPPORT_UTF8 +#ifndef NOUTF8 +#define NOUTF8 +#endif +#endif /* Other parameters */ @@ -103,6 +162,8 @@ #endif #endif +/* This is the default loop count for timing. */ + #define LOOPREPEAT 500000 /* Static variables */ @@ -113,7 +174,9 @@ static int callout_extra; static int callout_fail_count; static int callout_fail_id; +static int debug_lengths; static int first_callout; +static int locale_set = 0; static int show_malloc; static int use_utf8; static size_t gotten_store; @@ -143,6 +206,7 @@ Arguments: f the file to read start where in buffer to start (this *must* be within buffer) + prompt for stdin or readline() Returns: pointer to the start of new data could be a copy of start, or could be moved @@ -150,18 +214,47 @@ */ static uschar * -extend_inputline(FILE *f, uschar *start) +extend_inputline(FILE *f, uschar *start, const char *prompt) { uschar *here = start; for (;;) { int rlen = buffer_size - (here - buffer); + if (rlen > 1000) { int dlen; - if (fgets((char *)here, rlen, f) == NULL) - return (here == start)? NULL : start; + + /* If libreadline support is required, use readline() to read a line if the + input is a terminal. Note that readline() removes the trailing newline, so + we must put it back again, to be compatible with fgets(). */ + +#ifdef SUPPORT_LIBREADLINE + if (isatty(fileno(f))) + { + size_t len; + char *s = readline(prompt); + if (s == NULL) return (here == start)? NULL : start; + len = strlen(s); + if (len > 0) add_history(s); + if (len > rlen - 1) len = rlen - 1; + memcpy(here, s, len); + here[len] = '\n'; + here[len+1] = 0; + free(s); + } + else +#endif + + /* Read the next line by normal means, prompting if the file is stdin. */ + + { + if (f == stdin) printf(prompt); + if (fgets((char *)here, rlen, f) == NULL) + return (here == start)? NULL : start; + } + dlen = (int)strlen((char *)here); if (dlen > 0 && here[dlen - 1] == '\n') return start; here += dlen; @@ -213,7 +306,7 @@ /* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess around with conditional compilation, just do the job by hand. It is only used -for unpicking the -o argument, so just keep it simple. +for unpicking arguments, so just keep it simple. Arguments: str string to be converted @@ -311,6 +404,8 @@ Returns: number of characters placed in the buffer */ +#if !defined NOUTF8 + static int ord2utf8(int cvalue, uschar *utf8bytes) { @@ -327,6 +422,8 @@ return i + 1; } +#endif + /************************************************* @@ -353,16 +450,19 @@ { length -= rc - 1; p += rc; - if (c < 256 && isprint(c)) + if (PRINTHEX(c)) { if (f != NULL) fprintf(f, "%c", c); yield++; } else { - int n; - if (f != NULL) fprintf(f, "\\x{%02x}%n", c, &n); - yield += n; + int n = 4; + if (f != NULL) fprintf(f, "\\x{%02x}", c); + yield += (n <= 0x000000ff)? 2 : + (n <= 0x00000fff)? 3 : + (n <= 0x0000ffff)? 4 : + (n <= 0x000fffff)? 5 : 6; } continue; } @@ -371,7 +471,8 @@ /* Not UTF-8, or malformed UTF-8 */ - if (isprint(c = *(p++))) + c = *p++; + if (PRINTHEX(c)) { if (f != NULL) fprintf(f, "%c", c); yield++; @@ -610,11 +711,38 @@ /************************************************* +* Case-independent strncmp() function * +*************************************************/ + +/* +Arguments: + s first string + t second string + n number of characters to compare + +Returns: < 0, = 0, or > 0, according to the comparison +*/ + +static int +strncmpic(uschar *s, uschar *t, int n) +{ +while (n--) + { + int c = tolower(*s++) - tolower(*t++); + if (c) return c; + } +return 0; +} + + + +/************************************************* * Check newline indicator * *************************************************/ /* This is used both at compile and run-time to check for <xxx> escapes, where -xxx is LF, CR, or CRLF. Print a message and return 0 if there is no match. +xxx is LF, CR, CRLF, ANYCRLF, or ANY. Print a message and return 0 if there is +no match. Arguments: p points after the leading '<' @@ -626,9 +754,13 @@ static int check_newline(uschar *p, FILE *f) { -if (strncmp((char *)p, "cr>", 3) == 0) return PCRE_NEWLINE_CR; -if (strncmp((char *)p, "lf>", 3) == 0) return PCRE_NEWLINE_LF; -if (strncmp((char *)p, "crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; +if (strncmpic(p, (uschar *)"cr>", 3) == 0) return PCRE_NEWLINE_CR; +if (strncmpic(p, (uschar *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; +if (strncmpic(p, (uschar *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; +if (strncmpic(p, (uschar *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; +if (strncmpic(p, (uschar *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; +if (strncmpic(p, (uschar *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; +if (strncmpic(p, (uschar *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; fprintf(f, "Unknown newline type at: <%s\n", p); return 0; } @@ -636,6 +768,46 @@ /************************************************* +* Usage function * +*************************************************/ + +static void +usage(void) +{ +printf("Usage: pcretest [options] [<input file> [<output file>]]\n\n"); +printf("Input and output default to stdin and stdout.\n"); +#ifdef SUPPORT_LIBREADLINE +printf("If input is a terminal, readline() is used to read from it.\n"); +#else +printf("This version of pcretest is not linked with readline().\n"); +#endif +printf("\nOptions:\n"); +printf(" -b show compiled code (bytecode)\n"); +printf(" -C show PCRE compile-time options and exit\n"); +printf(" -d debug: show compiled code and information (-b and -i)\n"); +#if !defined NODFA +printf(" -dfa force DFA matching for all subjects\n"); +#endif +printf(" -help show usage information\n"); +printf(" -i show information about compiled patterns\n" + " -M find MATCH_LIMIT minimum for each subject\n" + " -m output memory used information\n" + " -o <n> set size of offsets vector to <n>\n"); +#if !defined NOPOSIX +printf(" -p use POSIX interface\n"); +#endif +printf(" -q quiet: do not output PCRE version number at start\n"); +printf(" -S <n> set stack size to <n> megabytes\n"); +printf(" -s output store (memory) used information\n" + " -t time compilation and execution\n"); +printf(" -t <n> time compilation and execution, repeating <n> times\n"); +printf(" -tm time execution (matching) only\n"); +printf(" -tm <n> time execution (matching) only, repeating <n> times\n"); +} + + + +/************************************************* * Main Program * *************************************************/ @@ -648,8 +820,10 @@ FILE *infile = stdin; int options = 0; int study_options = 0; +int default_find_match_limit = FALSE; int op = 1; int timeit = 0; +int timeitm = 0; int showinfo = 0; int showstore = 0; int quiet = 0; @@ -681,16 +855,19 @@ dbuffer = (unsigned char *)malloc(buffer_size); pbuffer = (unsigned char *)malloc(buffer_size); -/* The outfile variable is static so that new_malloc can use it. The _setmode() -stuff is some magic that I don't understand, but which apparently does good -things in Windows. It's related to line terminations. */ - -#if defined(_WIN32) || defined(WIN32) -_setmode( _fileno( stdout ), 0x8000 ); -#endif /* defined(_WIN32) || defined(WIN32) */ +/* The outfile variable is static so that new_malloc can use it. */ outfile = stdout; +/* The following _setmode() stuff is some Windows magic that tells its runtime +library to translate CRLF into a single LF character. At least, that's what +I've been told: never having used Windows I take this all on trust. Originally +it set 0x8000, but then I was advised that _O_BINARY was better. */ + +#if defined(_WIN32) || defined(WIN32) +_setmode( _fileno( stdout ), _O_BINARY ); +#endif + /* Scan options */ while (argc > 1 && argv[op][0] == '-') @@ -699,10 +876,11 @@ if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) showstore = 1; - else if (strcmp(argv[op], "-t") == 0) timeit = 1; else if (strcmp(argv[op], "-q") == 0) quiet = 1; + else if (strcmp(argv[op], "-b") == 0) debug = 1; else if (strcmp(argv[op], "-i") == 0) showinfo = 1; else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; + else if (strcmp(argv[op], "-M") == 0) default_find_match_limit = TRUE; #if !defined NODFA else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; #endif @@ -713,11 +891,25 @@ op++; argc--; } + else if (strcmp(argv[op], "-t") == 0 || strcmp(argv[op], "-tm") == 0) + { + int both = argv[op][2] == 0; + int temp; + if (argc > 2 && (temp = get_value((unsigned char *)argv[op+1], &endptr), + *endptr == 0)) + { + timeitm = temp; + op++; + argc--; + } + else timeitm = LOOPREPEAT; + if (both) timeit = timeitm; + } else if (strcmp(argv[op], "-S") == 0 && argc > 2 && ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), *endptr == 0)) { -#ifdef _WIN32 +#if defined(_WIN32) || defined(WIN32) printf("PCRE: -S not supported on this OS\n"); exit(1); #else @@ -741,6 +933,7 @@ else if (strcmp(argv[op], "-C") == 0) { int rc; + unsigned long int lrc; printf("PCRE version %s\n", pcre_version()); printf("Compiled with\n"); (void)pcre_config(PCRE_CONFIG_UTF8, &rc); @@ -748,38 +941,37 @@ (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); printf(" %sUnicode properties support\n", rc? "" : "No "); (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); - printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : - (rc == '\n')? "LF" : "CRLF"); + /* Note that these values are always the ASCII values, even + in EBCDIC environments. CR is 13 and NL is 10. */ + printf(" Newline sequence is %s\n", (rc == 13)? "CR" : + (rc == 10)? "LF" : (rc == (13<<8 | 10))? "CRLF" : + (rc == -2)? "ANYCRLF" : + (rc == -1)? "ANY" : "???"); + (void)pcre_config(PCRE_CONFIG_BSR, &rc); + printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : + "all Unicode newlines"); (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); printf(" Internal link size = %d\n", rc); (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); printf(" POSIX malloc threshold = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &rc); - printf(" Default match limit = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &rc); - printf(" Default recursion depth limit = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &lrc); + printf(" Default match limit = %ld\n", lrc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &lrc); + printf(" Default recursion depth limit = %ld\n", lrc); (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); printf(" Match recursion uses %s\n", rc? "stack" : "heap"); - exit(0); + goto EXIT; + } + else if (strcmp(argv[op], "-help") == 0 || + strcmp(argv[op], "--help") == 0) + { + usage(); + goto EXIT; } else { printf("** Unknown or malformed option %s\n", argv[op]); - printf("Usage: pcretest [options] [<input> [<output>]]\n"); - printf(" -C show PCRE compile-time options and exit\n"); - printf(" -d debug: show compiled code; implies -i\n"); -#if !defined NODFA - printf(" -dfa force DFA matching for all subjects\n"); -#endif - printf(" -i show information about compiled pattern\n" - " -m output memory used information\n" - " -o <n> set size of offsets vector to <n>\n"); -#if !defined NOPOSIX - printf(" -p use POSIX interface\n"); -#endif - printf(" -S <n> set stack size to <n> megabytes\n"); - printf(" -s output store (memory) used information\n" - " -t time compilation and execution\n"); + usage(); yield = 1; goto EXIT; } @@ -794,7 +986,7 @@ if (offsets == NULL) { printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * (int)sizeof(int)); + (int)(size_offsets_max * sizeof(int))); yield = 1; goto EXIT; } @@ -803,7 +995,7 @@ if (argc > 1) { - infile = fopen(argv[op], "rb"); + infile = fopen(argv[op], INPUT_MODE); if (infile == NULL) { printf("** Failed to open %s\n", argv[op]); @@ -814,7 +1006,7 @@ if (argc > 2) { - outfile = fopen(argv[op+1], "wb"); + outfile = fopen(argv[op+1], OUTPUT_MODE); if (outfile == NULL) { printf("** Failed to open %s\n", argv[op+1]); @@ -859,12 +1051,12 @@ int do_showinfo = showinfo; int do_showrest = 0; int do_flip = 0; - int erroroffset, len, delimiter; + int erroroffset, len, delimiter, poffset; use_utf8 = 0; + debug_lengths = 1; - if (infile == stdin) printf(" re> "); - if (extend_inputline(infile, buffer) == NULL) break; + if (extend_inputline(infile, buffer, " re> ") == NULL) break; if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); fflush(outfile); @@ -964,11 +1156,12 @@ if (isalnum(delimiter) || delimiter == '\\') { - fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); + fprintf(outfile, "** Delimiter must not be alphanumeric or \\\n"); goto SKIP_DATA; } pp = p; + poffset = p - buffer; for(;;) { @@ -979,8 +1172,7 @@ pp++; } if (*pp != 0) break; - if (infile == stdin) printf(" > "); - if ((pp = extend_inputline(infile, pp)) == NULL) + if ((pp = extend_inputline(infile, pp, " > ")) == NULL) { fprintf(outfile, "** Unexpected EOF\n"); done = 1; @@ -989,6 +1181,11 @@ if (infile != stdin) fprintf(outfile, "%s", (char *)pp); } + /* The buffer may have moved while being extended; reset the start of data + pointer to the correct relative point in the buffer. */ + + p = buffer + poffset; + /* If the first character after the delimiter is backslash, make the pattern end with backslash. This is purely to provide a way of testing for the error message when a pattern ends with backslash. */ @@ -1020,6 +1217,7 @@ case '+': do_showrest = 1; break; case 'A': options |= PCRE_ANCHORED; break; + case 'B': do_debug = 1; break; case 'C': options |= PCRE_AUTO_CALLOUT; break; case 'D': do_debug = do_showinfo = 1; break; case 'E': options |= PCRE_DOLLAR_ENDONLY; break; @@ -1037,19 +1235,22 @@ case 'S': do_study = 1; break; case 'U': options |= PCRE_UNGREEDY; break; case 'X': options |= PCRE_EXTRA; break; + case 'Z': debug_lengths = 0; break; case '8': options |= PCRE_UTF8; use_utf8 = 1; break; case '?': options |= PCRE_NO_UTF8_CHECK; break; case 'L': ppp = pp; - /* The '\r' test here is so that it works on Windows */ - while (*ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; + /* The '\r' test here is so that it works on Windows. */ + /* The '0' test is just in case this is an unterminated line. */ + while (*ppp != 0 && *ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; *ppp = 0; if (setlocale(LC_CTYPE, (const char *)pp) == NULL) { fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); goto SKIP_DATA; } + locale_set = 1; tables = pcre_maketables(); pp = ppp; break; @@ -1063,10 +1264,18 @@ case '<': { - int x = check_newline(pp, outfile); - if (x == 0) goto SKIP_DATA; - options |= x; - while (*pp++ != '>'); + if (strncmp((char *)pp, "JS>", 3) == 0) + { + options |= PCRE_JAVASCRIPT_COMPAT; + pp += 3; + } + else + { + int x = check_newline(pp, outfile); + if (x == 0) goto SKIP_DATA; + options |= x; + while (*pp++ != '>'); + } } break; @@ -1116,19 +1325,21 @@ #endif /* !defined NOPOSIX */ { - if (timeit) + unsigned long int get_options; + + if (timeit > 0) { register int i; clock_t time_taken; clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) + for (i = 0; i < timeit; i++) { re = pcre_compile((char *)p, options, &error, &erroroffset, tables); if (re != NULL) free(re); } time_taken = clock() - start_time; - fprintf(outfile, "Compile time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + fprintf(outfile, "Compile time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeit) / (double)CLOCKS_PER_SEC); } @@ -1145,7 +1356,7 @@ { for (;;) { - if (extend_inputline(infile, buffer) == NULL) + if (extend_inputline(infile, buffer, NULL) == NULL) { done = 1; goto CONTINUE; @@ -1159,9 +1370,16 @@ goto CONTINUE; } - /* Compilation succeeded; print data if required. There are now two - info-returning functions. The old one has a limited interface and - returns only limited data. Check that it agrees with the newer one. */ + /* Compilation succeeded. It is now possible to set the UTF-8 option from + within the regex; check for this so that we know how to process the data + lines. */ + + new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); + if ((get_options & PCRE_UTF8) != 0) use_utf8 = 1; + + /* Print information if required. There are now two info-returning + functions. The old one has a limited interface and returns only limited + data. Check that it agrees with the newer one. */ if (log_store) fprintf(outfile, "Memory allocation (code space): %d\n", @@ -1180,17 +1398,17 @@ if (do_study) { - if (timeit) + if (timeit > 0) { register int i; clock_t time_taken; clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) + for (i = 0; i < timeit; i++) extra = pcre_study(re, study_options, &error); time_taken = clock() - start_time; if (extra != NULL) free(extra); - fprintf(outfile, " Study time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + fprintf(outfile, " Study time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeit) / (double)CLOCKS_PER_SEC); } extra = pcre_study(re, study_options, &error); @@ -1208,18 +1426,25 @@ if (do_flip) { real_pcre *rre = (real_pcre *)re; - rre->magic_number = byteflip(rre->magic_number, sizeof(rre->magic_number)); + rre->magic_number = + byteflip(rre->magic_number, sizeof(rre->magic_number)); rre->size = byteflip(rre->size, sizeof(rre->size)); rre->options = byteflip(rre->options, sizeof(rre->options)); - rre->top_bracket = byteflip(rre->top_bracket, sizeof(rre->top_bracket)); - rre->top_backref = byteflip(rre->top_backref, sizeof(rre->top_backref)); - rre->first_byte = byteflip(rre->first_byte, sizeof(rre->first_byte)); - rre->req_byte = byteflip(rre->req_byte, sizeof(rre->req_byte)); - rre->name_table_offset = byteflip(rre->name_table_offset, + rre->flags = (pcre_uint16)byteflip(rre->flags, sizeof(rre->flags)); + rre->top_bracket = + (pcre_uint16)byteflip(rre->top_bracket, sizeof(rre->top_bracket)); + rre->top_backref = + (pcre_uint16)byteflip(rre->top_backref, sizeof(rre->top_backref)); + rre->first_byte = + (pcre_uint16)byteflip(rre->first_byte, sizeof(rre->first_byte)); + rre->req_byte = + (pcre_uint16)byteflip(rre->req_byte, sizeof(rre->req_byte)); + rre->name_table_offset = (pcre_uint16)byteflip(rre->name_table_offset, sizeof(rre->name_table_offset)); - rre->name_entry_size = byteflip(rre->name_entry_size, + rre->name_entry_size = (pcre_uint16)byteflip(rre->name_entry_size, sizeof(rre->name_entry_size)); - rre->name_count = byteflip(rre->name_count, sizeof(rre->name_count)); + rre->name_count = (pcre_uint16)byteflip(rre->name_count, + sizeof(rre->name_count)); if (extra != NULL) { @@ -1233,23 +1458,25 @@ SHOW_INFO: + if (do_debug) + { + fprintf(outfile, "------------------------------------------------------------------\n"); + pcre_printint(re, outfile, debug_lengths); + } + + /* We already have the options in get_options (see above) */ + if (do_showinfo) { - unsigned long int get_options, all_options; + unsigned long int all_options; #if !defined NOINFOCHECK int old_first_char, old_options, old_count; #endif - int count, backrefmax, first_char, need_char; + int count, backrefmax, first_char, need_char, okpartial, jchanged, + hascrorlf; int nameentrysize, namecount; const uschar *nametable; - if (do_debug) - { - fprintf(outfile, "------------------------------------------------------------------\n"); - pcre_printint(re, outfile); - } - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); new_info(re, NULL, PCRE_INFO_SIZE, &size); new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); @@ -1258,6 +1485,9 @@ new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); + new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial); + new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged); + new_info(re, NULL, PCRE_INFO_HASCRORLF, &hascrorlf); #if !defined NOINFOCHECK old_count = pcre_info(re, &old_options, &old_first_char); @@ -1299,26 +1529,22 @@ } } - /* The NOPARTIAL bit is a private bit in the options, so we have - to fish it out via out back door */ + if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); + if (hascrorlf) fprintf(outfile, "Contains explicit CR or LF match\n"); all_options = ((real_pcre *)re)->options; - if (do_flip) - { - all_options = byteflip(all_options, sizeof(all_options)); - } - - if ((all_options & PCRE_NOPARTIAL) != 0) - fprintf(outfile, "Partial matching not supported\n"); + if (do_flip) all_options = byteflip(all_options, sizeof(all_options)); if (get_options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", + ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", + ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", ((get_options & PCRE_EXTRA) != 0)? " extra" : "", ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", @@ -1327,7 +1553,9 @@ ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); - switch (get_options & PCRE_NEWLINE_CRLF) + if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); + + switch (get_options & PCRE_NEWLINE_BITS) { case PCRE_NEWLINE_CR: fprintf(outfile, "Forced newline sequence: CR\n"); @@ -1341,6 +1569,14 @@ fprintf(outfile, "Forced newline sequence: CRLF\n"); break; + case PCRE_NEWLINE_ANYCRLF: + fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); + break; + + case PCRE_NEWLINE_ANY: + fprintf(outfile, "Forced newline sequence: ANY\n"); + break; + default: break; } @@ -1358,7 +1594,7 @@ int ch = first_char & 255; const char *caseless = ((first_char & REQ_CASELESS) == 0)? "" : " (caseless)"; - if (isprint(ch)) + if (PRINTHEX(ch)) fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); else fprintf(outfile, "First char = %d%s\n", ch, caseless); @@ -1373,7 +1609,7 @@ int ch = need_char & 255; const char *caseless = ((need_char & REQ_CASELESS) == 0)? "" : " (caseless)"; - if (isprint(ch)) + if (PRINTHEX(ch)) fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); else fprintf(outfile, "Need char = %d%s\n", ch, caseless); @@ -1409,7 +1645,7 @@ fprintf(outfile, "\n "); c = 2; } - if (isprint(i) && i != ' ') + if (PRINTHEX(i) && i != ' ') { fprintf(outfile, "%c ", i); c += 2; @@ -1441,15 +1677,15 @@ else { uschar sbuf[8]; - sbuf[0] = (true_size >> 24) & 255; - sbuf[1] = (true_size >> 16) & 255; - sbuf[2] = (true_size >> 8) & 255; - sbuf[3] = (true_size) & 255; - - sbuf[4] = (true_study_size >> 24) & 255; - sbuf[5] = (true_study_size >> 16) & 255; - sbuf[6] = (true_study_size >> 8) & 255; - sbuf[7] = (true_study_size) & 255; + sbuf[0] = (uschar)((true_size >> 24) & 255); + sbuf[1] = (uschar)((true_size >> 16) & 255); + sbuf[2] = (uschar)((true_size >> 8) & 255); + sbuf[3] = (uschar)((true_size) & 255); + + sbuf[4] = (uschar)((true_study_size >> 24) & 255); + sbuf[5] = (uschar)((true_study_size >> 16) & 255); + sbuf[6] = (uschar)((true_study_size >> 8) & 255); + sbuf[7] = (uschar)((true_study_size) & 255); if (fwrite(sbuf, 1, 8, f) < 8 || fwrite(re, 1, true_size, f) < true_size) @@ -1468,6 +1704,7 @@ strerror(errno)); } else fprintf(outfile, "Study data written to %s\n", to_file); + } } fclose(f); @@ -1485,14 +1722,14 @@ for (;;) { uschar *q; - uschar *bptr = dbuffer; + uschar *bptr; int *use_offsets = offsets; int use_size_offsets = size_offsets; int callout_data = 0; int callout_data_set = 0; int count, c; int copystrings = 0; - int find_match_limit = 0; + int find_match_limit = default_find_match_limit; int getstrings = 0; int getlist = 0; int gmatched = 0; @@ -1522,8 +1759,7 @@ len = 0; for (;;) { - if (infile == stdin) printf("data> "); - if (extend_inputline(infile, buffer + len) == NULL) + if (extend_inputline(infile, buffer + len, "data> ") == NULL) { if (len > 0) break; done = 1; @@ -1541,7 +1777,7 @@ p = buffer; while (isspace(*p)) p++; - q = dbuffer; + bptr = q = dbuffer; while ((c = *p++) != 0) { int i = 0; @@ -1591,9 +1827,19 @@ { unsigned char buff8[8]; int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ + if (use_utf8) + { + utn = ord2utf8(c, buff8); + for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; + c = buff8[ii]; /* Last byte */ + } + else + { + if (c > 255) + fprintf(outfile, "** Character \\x{%x} is greater than 255 and " + "UTF-8 mode is not enabled.\n" + "** Truncation will probably give the wrong result.\n", c); + } p = pt + 1; break; } @@ -1736,7 +1982,7 @@ if (offsets == NULL) { printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * (int)sizeof(int)); + (int)(size_offsets_max * sizeof(int))); yield = 1; goto EXIT; } @@ -1781,6 +2027,10 @@ show_malloc = 1; continue; + case 'Y': + options |= PCRE_NO_START_OPTIMIZE; + continue; + case 'Z': options |= PCRE_NOTEOL; continue; @@ -1803,6 +2053,23 @@ *q = 0; len = q - dbuffer; + /* Move the data to the end of the buffer so that a read over the end of + the buffer will be seen by valgrind, even if it doesn't cause a crash. If + we are using the POSIX interface, we must include the terminating zero. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + memmove(bptr + buffer_size - len - 1, bptr, len + 1); + bptr += buffer_size - len - 1; + } + else +#endif + { + memmove(bptr + buffer_size - len, bptr, len); + bptr += buffer_size - len; + } + if ((all_use_dfa || use_dfa) && find_match_limit) { printf("**Match limit not relevant for DFA matching: ignored\n"); @@ -1822,6 +2089,7 @@ pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; + if ((options & PCRE_NOTEMPTY) != 0) eflags |= REG_NOTEMPTY; rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); @@ -1866,7 +2134,7 @@ for (;; gmatched++) /* Loop for /g or /G */ { - if (timeit) + if (timeitm > 0) { register int i; clock_t time_taken; @@ -1876,7 +2144,7 @@ if (all_use_dfa || use_dfa) { int workspace[1000]; - for (i = 0; i < LOOPREPEAT; i++) + for (i = 0; i < timeitm; i++) count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, options | g_notempty, use_offsets, use_size_offsets, workspace, sizeof(workspace)/sizeof(int)); @@ -1884,13 +2152,13 @@ else #endif - for (i = 0; i < LOOPREPEAT; i++) + for (i = 0; i < timeitm; i++) count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options | g_notempty, use_offsets, use_size_offsets); time_taken = clock() - start_time; - fprintf(outfile, "Execute time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + fprintf(outfile, "Execute time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeitm) / (double)CLOCKS_PER_SEC); } @@ -1966,7 +2234,28 @@ if (count >= 0) { - int i; + int i, maxcount; + +#if !defined NODFA + if (all_use_dfa || use_dfa) maxcount = use_size_offsets/2; else +#endif + maxcount = use_size_offsets/3; + + /* This is a check against a lunatic return value. */ + + if (count > maxcount) + { + fprintf(outfile, + "** PCRE error: returned count %d is too big for offset size %d\n", + count, use_size_offsets); + count = use_size_offsets/3; + if (do_g || do_G) + { + fprintf(outfile, "** /%c loop abandoned\n", do_g? 'g' : 'G'); + do_g = do_G = FALSE; /* Break g/G loop */ + } + } + for (i = 0; i < count * 2; i += 2) { if (use_offsets[i] < 0) @@ -2084,19 +2373,46 @@ } /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. - We want to advance the start offset, and continue. In the case of UTF-8 - matching, the advance must be one character, not one byte. Fudge the - offset values to achieve this. We won't be at the end of the string - - that was checked before setting g_notempty. */ + g_notempty after a null match, this is not necessarily the end. We want + to advance the start offset, and continue. We won't be at the end of the + string - that was checked before setting g_notempty. + + Complication arises in the case when the newline option is "any" or + "anycrlf". If the previous match was at the end of a line terminated by + CRLF, an advance of one character just passes the \r, whereas we should + prefer the longer newline sequence, as does the code in pcre_exec(). + Fudge the offset value to achieve this. + + Otherwise, in the case of UTF-8 matching, the advance must be one + character, not one byte. */ else { if (g_notempty != 0) { int onechar = 1; + unsigned int obits = ((real_pcre *)re)->options; use_offsets[0] = start_offset; - if (use_utf8) + if ((obits & PCRE_NEWLINE_BITS) == 0) + { + int d; + (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); + /* Note that these values are always the ASCII ones, even in + EBCDIC environments. CR = 13, NL = 10. */ + obits = (d == 13)? PCRE_NEWLINE_CR : + (d == 10)? PCRE_NEWLINE_LF : + (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : + (d == -2)? PCRE_NEWLINE_ANYCRLF : + (d == -1)? PCRE_NEWLINE_ANY : 0; + } + if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || + (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) + && + start_offset < len - 1 && + bptr[start_offset] == '\r' && + bptr[start_offset+1] == '\n') + onechar++; + else if (use_utf8) { while (start_offset + onechar < len) { @@ -2131,6 +2447,7 @@ character. */ g_notempty = 0; + if (use_offsets[0] == use_offsets[1]) { if (use_offsets[0] == len) break; @@ -2165,6 +2482,7 @@ { new_free((void *)tables); setlocale(LC_CTYPE, "C"); + locale_set = 0; } } Added: freeswitch/trunk/libs/pcre/perltest.pl ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/perltest.pl Mon Jun 8 18:51:30 2009 @@ -0,0 +1,191 @@ +#! /usr/bin/env perl + +# Program for testing regular expressions with perl to check that PCRE handles +# them the same. This is the version that supports /8 for UTF-8 testing. As it +# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to +# have "use utf8" at the start for running the UTF-8 tests, but *not* for the +# other tests. The only way I've found for doing this is to cat this line in +# explicitly in the RunPerlTest script. + +# use locale; # With this included, \x0b matches \s! + +# Function for turning a string into a string of printing chars. There are +# currently problems with UTF-8 strings; this fudges round them. + +sub pchars { +my($t) = ""; + +if ($utf8) + { + @p = unpack('U*', $_[0]); + foreach $c (@p) + { + if ($c >= 32 && $c < 127) { $t .= chr $c; } + else { $t .= sprintf("\\x{%02x}", $c); } + } + } + +else + { + foreach $c (split(//, $_[0])) + { + if (ord $c >= 32 && ord $c < 127) { $t .= $c; } + else { $t .= sprintf("\\x%02x", ord $c); } + } + } + +$t; +} + + +# Read lines from named file or stdin and write to named file or stdout; lines +# consist of a regular expression, in delimiters and optionally followed by +# options, followed by a set of test data, terminated by an empty line. + +# Sort out the input and output files + +if (@ARGV > 0) + { + open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; + $infile = "INFILE"; + } +else { $infile = "STDIN"; } + +if (@ARGV > 1) + { + open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; + $outfile = "OUTFILE"; + } +else { $outfile = "STDOUT"; } + +printf($outfile "Perl $] Regular Expressions\n\n"); + +# Main loop + +NEXT_RE: +for (;;) + { + printf " re> " if $infile eq "STDIN"; + last if ! ($_ = <$infile>); + printf $outfile "$_" if $infile ne "STDIN"; + next if ($_ eq ""); + + $pattern = $_; + + while ($pattern !~ /^\s*(.).*\1/s) + { + printf " > " if $infile eq "STDIN"; + last if ! ($_ = <$infile>); + printf $outfile "$_" if $infile ne "STDIN"; + $pattern .= $_; + } + + chomp($pattern); + $pattern =~ s/\s+$//; + + # The private /+ modifier means "print $' afterwards". + + $showrest = ($pattern =~ s/\+(?=[a-z]*$)//); + + # Remove /8 from a UTF-8 pattern. + + $utf8 = $pattern =~ s/8(?=[a-z]*$)//; + + # Check that the pattern is valid + + eval "\$_ =~ ${pattern}"; + if ($@) + { + printf $outfile "Error: $@"; + next NEXT_RE; + } + + # If the /g modifier is present, we want to put a loop round the matching; + # otherwise just a single "if". + + $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; + + # If the pattern is actually the null string, Perl uses the most recently + # executed (and successfully compiled) regex is used instead. This is a + # nasty trap for the unwary! The PCRE test suite does contain null strings + # in places - if they are allowed through here all sorts of weird and + # unexpected effects happen. To avoid this, we replace such patterns with + # a non-null pattern that has the same effect. + + $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); + + # Read data lines and test them + + for (;;) + { + printf "data> " if $infile eq "STDIN"; + last NEXT_RE if ! ($_ = <$infile>); + chomp; + printf $outfile "$_\n" if $infile ne "STDIN"; + + s/\s+$//; + s/^\s+//; + + last if ($_ eq ""); + $x = eval "\"$_\""; # To get escapes processed + + # Empty array for holding results, then do the matching. + + @subs = (); + + $pushes = "push \@subs,\$&;" . + "push \@subs,\$1;" . + "push \@subs,\$2;" . + "push \@subs,\$3;" . + "push \@subs,\$4;" . + "push \@subs,\$5;" . + "push \@subs,\$6;" . + "push \@subs,\$7;" . + "push \@subs,\$8;" . + "push \@subs,\$9;" . + "push \@subs,\$10;" . + "push \@subs,\$11;" . + "push \@subs,\$12;" . + "push \@subs,\$13;" . + "push \@subs,\$14;" . + "push \@subs,\$15;" . + "push \@subs,\$16;" . + "push \@subs,\$'; }"; + + eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; + + if ($@) + { + printf $outfile "Error: $@\n"; + next NEXT_RE; + } + elsif (scalar(@subs) == 0) + { + printf $outfile "No match\n"; + } + else + { + while (scalar(@subs) != 0) + { + printf $outfile (" 0: %s\n", &pchars($subs[0])); + printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; + $last_printed = 0; + for ($i = 1; $i <= 16; $i++) + { + if (defined $subs[$i]) + { + while ($last_printed++ < $i-1) + { printf $outfile ("%2d: <unset>\n", $last_printed); } + printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); + $last_printed = $i; + } + } + splice(@subs, 0, 18); + } + } + } + } + +# printf $outfile "\n"; + +# End Added: freeswitch/trunk/libs/pcre/testdata/grepinput8 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/grepinput8 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,11 @@ +X one +X twoX threeX four X five +X six +X seven…X eight
X nine
X ten + +Before 111 +Before 222
Before 333…Match +After 111 +After 222
After 333 +And so on and so on +And so on and so on Added: freeswitch/trunk/libs/pcre/testdata/grepinputv ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/grepinputv Mon Jun 8 18:51:30 2009 @@ -0,0 +1,4 @@ +The quick brown +fox jumps +over the lazy dog. +This time it jumps and jumps and jumps. Modified: freeswitch/trunk/libs/pcre/testdata/grepinputx ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/grepinputx (original) +++ freeswitch/trunk/libs/pcre/testdata/grepinputx Mon Jun 8 18:51:30 2009 @@ -39,10 +39,5 @@ nineteen twenty -Here follows some CR/LF/CRLF test data. - -abc def -ghi -jkl - +This line contains pattern not on a line by itself. This is the last line of this file. Modified: freeswitch/trunk/libs/pcre/testdata/grepoutput ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/grepoutput (original) +++ freeswitch/trunk/libs/pcre/testdata/grepoutput Mon Jun 8 18:51:30 2009 @@ -18,6 +18,7 @@ ./testdata/grepinput:608:Check up on PATTERN near the end. ./testdata/grepinputx:3:Here is the pattern again. ./testdata/grepinputx:5:Pattern +./testdata/grepinputx:42:This line contains pattern not on a line by itself. ---------------------------- Test 6 ------------------------------ 7:PATTERN at the start of a line. 8:In the middle of a line, PATTERN appears. @@ -25,6 +26,7 @@ 608:Check up on PATTERN near the end. 3:Here is the pattern again. 5:Pattern +42:This line contains pattern not on a line by itself. ---------------------------- Test 7 ------------------------------ ./testdata/grepinput ./testdata/grepinputx @@ -75,18 +77,13 @@ 39:nineteen 40:twenty 41: -42:Here follows some CR/LF/CRLF test data. -43: -44:abc def -45:ghi -46:jkl -47: -48:This is the last line of this file. +43:This is the last line of this file. ---------------------------- Test 12 ----------------------------- Pattern ---------------------------- Test 13 ----------------------------- Here is the pattern again. That time it was on a line by itself. +This line contains pattern not on a line by itself. ---------------------------- Test 14 ----------------------------- ./testdata/grepinputx:To pat or not to pat, that is the question. ---------------------------- Test 15 ----------------------------- @@ -163,8 +160,8 @@ nineteen twenty -Here follows some CR/LF/CRLF test data. - +This line contains pattern not on a line by itself. +This is the last line of this file. ---------------------------- Test 25 ----------------------------- 15- 16-complete pair @@ -214,8 +211,8 @@ nineteen twenty -Here follows some CR/LF/CRLF test data. - +This line contains pattern not on a line by itself. +This is the last line of this file. ---------------------------- Test 27 ----------------------------- four five @@ -235,9 +232,8 @@ nineteen twenty -Here follows some CR/LF/CRLF test data. - -abc def +This line contains pattern not on a line by itself. +This is the last line of this file. ---------------------------- Test 28 ----------------------------- 14-of lines all by themselves. 15- @@ -289,11 +285,8 @@ nineteen twenty -Here follows some CR/LF/CRLF test data. - -abc def -ghi -jkl +This line contains pattern not on a line by itself. +This is the last line of this file. ---------------------------- Test 30 ----------------------------- ./testdata/grepinput-4-features should be added at the end, because some of the tests involve the ./testdata/grepinput-5-output of line numbers, and we don't want these to change. @@ -313,6 +306,11 @@ ./testdata/grepinputx:3:Here is the pattern again. ./testdata/grepinputx-4- ./testdata/grepinputx:5:Pattern +-- +./testdata/grepinputx-39-nineteen +./testdata/grepinputx-40-twenty +./testdata/grepinputx-41- +./testdata/grepinputx:42:This line contains pattern not on a line by itself. ---------------------------- Test 31 ----------------------------- ./testdata/grepinput:7:PATTERN at the start of a line. ./testdata/grepinput:8:In the middle of a line, PATTERN appears. @@ -331,6 +329,9 @@ ./testdata/grepinputx-6-That time it was on a line by itself. ./testdata/grepinputx-7- ./testdata/grepinputx-8-To pat or not to pat, that is the question. +-- +./testdata/grepinputx:42:This line contains pattern not on a line by itself. +./testdata/grepinputx-43-This is the last line of this file. ---------------------------- Test 32 ----------------------------- ./testdata/grepinputx ---------------------------- Test 33 ----------------------------- @@ -342,6 +343,7 @@ ./testdata/grepinputx RC=0 ---------------------------- Test 36 ----------------------------- +./testdata/grepinput8 ./testdata/grepinputx RC=0 ---------------------------- Test 37 ----------------------------- @@ -349,11 +351,11 @@ aaaaa2 RC=0 ======== STDERR ======== -pcregrep: pcre_exec() error -8 while matching this line: +pcregrep: pcre_exec() error -8 while matching this text: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa pcregrep: error -8 means that a resource limit was exceeded pcregrep: check your regex for nested unlimited loops -pcregrep: pcre_exec() error -8 while matching this line: +pcregrep: pcre_exec() error -8 while matching this text: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa ---------------------------- Test 38 ------------------------------ This line contains a binary zero here >< for testing. @@ -371,10 +373,13 @@ ./testdata/grepinput:597:after the binary zero ---------------------------- Test 42 ------------------------------ 595:before +595:zero 596:zero 597:after +597:zero ---------------------------- Test 43 ------------------------------ 595:before +595:zero 596:zero 597:zero ---------------------------- Test 44 ------------------------------ @@ -396,22 +401,25 @@ AB.VE the turtle PUT NEW DATA ABOVE THIS LINE. ---------------------------- Test 49 ------------------------------ -abc def -ghi -jkl ---------------------------- Test 50 ------------------------------ -def +over the lazy dog. +This time it jumps and jumps and jumps. ---------------------------- Test 51 ------------------------------ -abc def -ghi -jkl +fox jumps +This time it jumps and jumps and jumps. ---------------------------- Test 52 ------------------------------ -def - -ghi -jkl - -This is the last line of this file. - +36972,6 +36990,4 +37024,4 +37066,5 +37083,4 ---------------------------- Test 53 ------------------------------ -jkl +595:15,6 +595:33,4 +596:28,4 +597:15,5 +597:32,4 +---------------------------- Test 54 ----------------------------- +Here is the pattern again. +That time it was on a line by itself. +This line contains pattern not on a line by itself. Added: freeswitch/trunk/libs/pcre/testdata/grepoutput8 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/grepoutput8 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,10 @@ +---------------------------- Test U1 ------------------------------ +1:X one +2:X two3:X three4:X four 5:X five +6:X six +7:X seven…8:X eight
9:X nine
10:X ten +---------------------------- Test U2 ------------------------------ +12-Before 111 +13-Before 222
14-Before 333…15:Match +16-After 111 +17-After 222
18-After 333 Added: freeswitch/trunk/libs/pcre/testdata/grepoutputN ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/grepoutputN Mon Jun 8 18:51:30 2009 @@ -0,0 +1,16 @@ +---------------------------- Test N1 ------------------------------ +1:abc 2:def ---------------------------- Test N2 ------------------------------ +1:abc def +2:ghi +jkl---------------------------- Test N3 ------------------------------ +2:def 3: +ghi +jkl---------------------------- Test N4 ------------------------------ +2:ghi +jkl---------------------------- Test N5 ------------------------------ +1:abc 2:def +3:ghi +4:jkl---------------------------- Test N6 ------------------------------ +1:abc 2:def +3:ghi +4:jkl \ No newline at end of file Modified: freeswitch/trunk/libs/pcre/testdata/testinput1 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput1 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput1 Mon Jun 8 18:51:30 2009 @@ -1297,7 +1297,7 @@ abc /^a b -  c/x +  c/x abc /^(a|)\1*b/ @@ -1453,11 +1453,6 @@ /{4,5a}bc/ {4,5a}bc -/^a.b/ - a\rb - *** Failers - a\nb - /abc$/ abc abc\n @@ -1499,8 +1494,8 @@ /(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ abcdefghijk\12S -/ab\gdef/ - abgdef +/ab\idef/ + abidef /a{0}bc/ bc @@ -3381,9 +3376,14 @@ cdaccb /^(?:a?b?)*$/ + \ + a + ab + aaa *** Failers dbcb a-- + aa-- /((?s)^a(.))((?m)^b$)/ a\nb\nc\n @@ -3421,11 +3421,6 @@ /((?m)^b)/ a\nb\nc\n -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - /(x)?(?(1)a|b)/ *** Failers a @@ -3883,4 +3878,190 @@ a,b] [a,b,c] +/(?-x: )/x + A\x20B + +"(?x)(?-x: \s*#\s*)" + A # B + ** Failers + # + +"(?x-is)(?:(?-ixs) \s*#\s*) include" + A #include + ** Failers + A#include + A #Include + +/a*b*\w/ + aaabbbb + aaaa + a + +/a*b?\w/ + aaabbbb + aaaa + a + +/a*b{0,4}\w/ + aaabbbb + aaaa + a + +/a*b{0,}\w/ + aaabbbb + aaaa + a + +/a*\d*\w/ + 0a + a + +/a*b *\w/x + a + +/a*b#comment + *\w/x + a + +/a* b *\w/x + a + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + +/(?=(\w+))\1:/ + abcd: + +/^(?=(\w+))\1:/ + abcd: + +/^\Eabc/ + abc + +/^[\Eabc]/ + a + ** Failers + E + +/^[a-\Ec]/ + b + ** Failers + - + E + +/^[a\E\E-\Ec]/ + b + ** Failers + - + E + +/^[\E\Qa\E-\Qz\E]+/ + b + ** Failers + - + +/^[a\Q]bc\E]/ + a + ] + c + +/^[a-\Q\E]/ + a + - + +/^(a()*)*/ + aaaa + +/^(?:a(?:(?:))*)*/ + aaaa + +/^(a()+)+/ + aaaa + +/^(?:a(?:(?:))+)+/ + aaaa + +/(a){0,3}(?(1)b|(c|))*D/ + abbD + ccccD + D + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/\Z/g + abc\n + +/^(?s)(?>.*)(?<!\n)/ + abc + abc\n + +/^(?![^\n]*\n\z)/ + abc + abc\n + +/\z(?<!\n)/ + abc + abc\n + +/(.*(.)?)*/ + abcd + +/( (A | (?(1)0|) )* )/x + abcd + +/( ( (?(1)0|) )* )/x + abcd + +/( (?(1)0|)* )/x + abcd + +/[[:abcd:xyz]]/ + a] + :] + +/[abc[:x\]pqr]/ + a + [ + : + ] + p + +/.*[op][xyz]/ + fooabcfoo + +/(?(?=.*b)b|^)/ + adc + abc + +/(?(?=^.*b)b|^)/ + adc + abc + +/(?(?=.*b)b|^)*/ + adc + abc + +/(?(?=.*b)b|^)+/ + adc + abc + +/(?(?=b).*b|^d)/ + abc + +/(?(?=.*b).*b|^d)/ + abc + +/^%((?(?=[a])[^%])|b)*%$/ + %ab% + / End of testinput1 / Added: freeswitch/trunk/libs/pcre/testdata/testinput10 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/testinput10 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,124 @@ +/-- These are a few representative patterns whose lengths and offsets are to be +shown when the link size is 2. This is just a doublecheck test to ensure the +sizes don't go horribly wrong when something is changed. The pattern contents +are all themselves checked in other tests. --/ + +/((?i)b)/BM + +/(?s)(.*X|^B)/BM + +/(?s:.*X|^B)/BM + +/^[[:alnum:]]/BM + +/#/IxMD + +/a#/IxMD + +/x?+/BM + +/x++/BM + +/x{1,3}+/BM + +/(x)*+/BM + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/BM + +|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM + +/(a(?1)b)/BM + +/(a(?1)+b)/BM + +/a(?P<name1>b|c)d(?P<longername2>e)/BM + +/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/BM + +/(?P<a>a)...(?P=a)bbb(?P>a)d/BM + +/abc(?C255)de(?C)f/BM + +/abcde/CBM + +/\x{100}/8BM + +/\x{1000}/8BM + +/\x{10000}/8BM + +/\x{100000}/8BM + +/\x{1000000}/8BM + +/\x{4000000}/8BM + +/\x{7fffFFFF}/8BM + +/[\x{ff}]/8BM + +/[\x{100}]/8BM + +/\x80/8BM + +/\xff/8BM + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8M + +/\x{D55c}\x{ad6d}\x{C5B4}/D8M + +/\x{65e5}\x{672c}\x{8a9e}/D8M + +/[\x{100}]/8BM + +/[Z\x{100}]/8BM + +/^[\x{100}\E-\Q\E\x{150}]/B8M + +/^[\QĀ\E-\QŐ\E]/B8M + +/^[\QĀ\E-\QŐ\E/B8M + +/[\p{L}]/BM + +/[\p{^L}]/BM + +/[\P{L}]/BM + +/[\P{^L}]/BM + +/[abc\p{L}\x{0660}]/8BM + +/[\p{Nd}]/8BM + +/[\p{Nd}+-]+/8BM + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM + +/[\x{105}-\x{109}]/8iBM + +/( ( (?(1)0|) )* )/xBM + +/( (?(1)0|)* )/xBM + +/[a]/BM + +/[a]/8BM + +/[\xaa]/BM + +/[\xaa]/8BM + +/[^a]/BM + +/[^a]/8BM + +/[^\xaa]/BM + +/[^\xaa]/8BM + +/ End of testinput10 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput2 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput2 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput2 Mon Jun 8 18:51:30 2009 @@ -1,6 +1,6 @@ -/(a)b|/ +/(a)b|/I -/abc/ +/abc/I abc defabc \Aabc @@ -8,29 +8,29 @@ \Adefabc ABC -/^abc/ +/^abc/I abc \Aabc *** Failers defabc \Adefabc -/a+bc/ +/a+bc/I -/a*bc/ +/a*bc/I -/a{3}bc/ +/a{3}bc/I -/(abc|a+z)/ +/(abc|a+z)/I -/^abc$/ +/^abc$/I abc *** Failers def\nabc -/ab\gdef/X +/ab\idef/X -/(?X)ab\gdef/X +/(?X)ab\idef/X /x{5,4}/ @@ -50,41 +50,41 @@ /(?z)abc/ -/.*b/ +/.*b/I -/.*?b/ +/.*?b/I -/cat|dog|elephant/ +/cat|dog|elephant/I this sentence eventually mentions a cat this sentences rambles on and on for a while and then reaches elephant -/cat|dog|elephant/S +/cat|dog|elephant/IS this sentence eventually mentions a cat this sentences rambles on and on for a while and then reaches elephant -/cat|dog|elephant/iS +/cat|dog|elephant/IiS this sentence eventually mentions a CAT cat this sentences rambles on and on for a while to elephant ElePhant -/a|[bcd]/S +/a|[bcd]/IS -/(a|[^\dZ])/S +/(a|[^\dZ])/IS -/(a|b)*[\s]/S +/(a|b)*[\s]/IS /(ab\2)/ /{4,5}abc/ -/(a)(b)(c)\2/ +/(a)(b)(c)\2/I abcb \O0abcb \O3abcb \O6abcb \O9abcb - \O12abcb + \O12abcb -/(a)bc|(a)(b)\2/ +/(a)bc|(a)(b)\2/I abc \O0abc \O3abc @@ -96,7 +96,7 @@ \O9aba \O12aba -/abc$/E +/abc$/IE abc *** Failers abc\n @@ -104,93 +104,93 @@ /(a)(b)(c)(d)(e)\6/ -/the quick brown fox/ +/the quick brown fox/I the quick brown fox this is a line with the quick brown fox -/the quick brown fox/A +/the quick brown fox/IA the quick brown fox *** Failers this is a line with the quick brown fox /ab(?z)cd/ -/^abc|def/ +/^abc|def/I abcdef abcdef\B -/.*((abc)$|(def))/ +/.*((abc)$|(def))/I defabc \Zdefabc -/abc/P +/abc/IP abc *** Failers - -/^abc|def/P + +/^abc|def/IP abcdef abcdef\B -/.*((abc)$|(def))/P +/.*((abc)$|(def))/IP defabc \Zdefabc - -/the quick brown fox/P + +/the quick brown fox/IP the quick brown fox - *** Failers - The Quick Brown Fox + *** Failers + The Quick Brown Fox -/the quick brown fox/Pi +/the quick brown fox/IPi the quick brown fox - The Quick Brown Fox + The Quick Brown Fox -/abc.def/P +/abc.def/IP *** Failers abc\ndef - -/abc$/P + +/abc$/IP abc - abc\n + abc\n -/(abc)\2/P +/(abc)\2/IP -/(abc\1)/P +/(abc\1)/IP abc /)/ /a[]b/ -/[^aeiou ]{3,}/ - co-processors, and for - -/<.*>/ +/[^aeiou ]{3,}/I + co-processors, and for + +/<.*>/I abc<def>ghi<klm>nop -/<.*?>/ +/<.*?>/I abc<def>ghi<klm>nop -/<.*>/U +/<.*>/IU abc<def>ghi<klm>nop - -/(?U)<.*>/ + +/(?U)<.*>/I abc<def>ghi<klm>nop -/<.*?>/U +/<.*?>/IU abc<def>ghi<klm>nop - -/={3,}/U + +/={3,}/IU abc========def - -/(?U)={3,}?/ + +/(?U)={3,}?/I abc========def - -/(?<!bar|cattle)foo/ + +/(?<!bar|cattle)foo/I foo - catfoo + catfoo *** Failers the barfoo - and cattlefoo + and cattlefoo /(?<=a+)b/ @@ -198,25 +198,25 @@ /(?<!(foo)a\1)bar/ -/(?i)abc/ +/(?i)abc/I -/(a|(?m)a)/ +/(a|(?m)a)/I -/(?i)^1234/ +/(?i)^1234/I -/(^b|(?i)^d)/ +/(^b|(?i)^d)/I -/(?s).*/ +/(?s).*/I -/[abcd]/S +/[abcd]/IS -/(?i)[abcd]/S +/(?i)[abcd]/IS -/(?m)[xy]|(b|c)/S +/(?m)[xy]|(b|c)/IS -/(^a|^b)/m +/(^a|^b)/Im -/(?i)(^a|^b)/m +/(?i)(^a|^b)/Im /(a)(?(1)a|b|c)/ @@ -224,66 +224,68 @@ /(?(1a)/ +/(?(1a))/ + /(?(?i))/ /(?(abc))/ /(?(?<ab))/ -/((?s)blah)\s+\1/ +/((?s)blah)\s+\1/I -/((?i)blah)\s+\1/ +/((?i)blah)\s+\1/I -/((?i)b)/DS +/((?i)b)/IDZS -/(a*b|(?i:c*(?-i)d))/S +/(a*b|(?i:c*(?-i)d))/IS -/a$/ +/a$/I a a\n - *** Failers + *** Failers \Za - \Za\n + \Za\n -/a$/m +/a$/Im a a\n - \Za\n - *** Failers + \Za\n + *** Failers \Za - -/\Aabc/m -/^abc/m +/\Aabc/Im + +/^abc/Im -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I aaaaabbbbbcccccdef -/(?<=foo)[ab]/S +/(?<=foo)[ab]/IS -/(?<!foo)(alpha|omega)/S +/(?<!foo)(alpha|omega)/IS -/(?!alphabet)[ab]/S +/(?!alphabet)[ab]/IS -/(?<=foo\n)^bar/m - foo\nbarbar +/(?<=foo\n)^bar/Im + foo\nbarbar ***Failers - rhubarb + rhubarb barbell - abc\nbarton + abc\nbarton -/^(?<=foo\n)bar/m - foo\nbarbar +/^(?<=foo\n)bar/Im + foo\nbarbar ***Failers - rhubarb + rhubarb barbell - abc\nbarton + abc\nbarton -/(?>^abc)/m +/(?>^abc)/Im abc def\nabc *** Failers - defabc + defabc /(?<=ab(c+)d)ef/ @@ -293,50 +295,50 @@ /The next three are in testinput2 because they have variable length branches/ -/(?<=bullock|donkey)-cart/ +/(?<=bullock|donkey)-cart/I the bullock-cart a donkey-cart race *** Failers cart - horse-and-cart - -/(?<=ab(?i)x|y|z)/ + horse-and-cart + +/(?<=ab(?i)x|y|z)/I -/(?>.*)(?<=(abcd)|(xyz))/ +/(?>.*)(?<=(abcd)|(xyz))/I alphabetabcd endingxyz -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I abxyZZ abXyZZ ZZZ zZZ bZZ - BZZ + BZZ *** Failers - ZZ - abXYZZ + ZZ + abXYZZ zzz - bzz + bzz -/(?<!(foo)a)bar/ +/(?<!(foo)a)bar/I bar - foobbar + foobbar *** Failers - fooabar + fooabar -/This one is here because Perl 5.005_02 doesn't fail it/ +/This one is here because Perl 5.005_02 doesn't fail it/I -/^(a)?(?(1)a|b)+$/ +/^(a)?(?(1)a|b)+$/I *** Failers - a + a -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ +/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/I -/^(a\1?){4}$/ +/^(a\1?){4}$/I aaaaaa - -/These are syntax tests from Perl 5.005/ + +/These are syntax tests from Perl 5.005/I /a[b-a]/ @@ -362,23 +364,23 @@ /(a)|\2/ -/a[b-a]/i +/a[b-a]/Ii -/a[]b/i +/a[]b/Ii -/a[/i +/a[/Ii -/*a/i +/*a/Ii -/(*)b/i +/(*)b/Ii -/abc)/i +/abc)/Ii -/(abc/i +/(abc/Ii -/a**/i +/a**/Ii -/)(/i +/)(/Ii /:(?:/ @@ -396,8 +398,6 @@ /(?(1?)a|b)/ -/(?(1)a|b|c)/ - /[a[:xyz:/ /(?<=x+)y/ @@ -410,190 +410,190 @@ /abc/\i -/(a)bc(d)/ +/(a)bc(d)/I abcd abcd\C2 abcd\C5 - -/(.{20})/ + +/(.{20})/I abcdefghijklmnopqrstuvwxyz abcdefghijklmnopqrstuvwxyz\C1 abcdefghijklmnopqrstuvwxyz\G1 - -/(.{15})/ + +/(.{15})/I abcdefghijklmnopqrstuvwxyz abcdefghijklmnopqrstuvwxyz\C1\G1 -/(.{16})/ +/(.{16})/I abcdefghijklmnopqrstuvwxyz abcdefghijklmnopqrstuvwxyz\C1\G1\L - -/^(a|(bc))de(f)/ - adef\G1\G2\G3\G4\L - bcdef\G1\G2\G3\G4\L - adefghijk\C0 - -/^abc\00def/ - abc\00def\L\C0 - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/M -/.*X/D +/^(a|(bc))de(f)/I + adef\G1\G2\G3\G4\L + bcdef\G1\G2\G3\G4\L + adefghijk\C0 -/.*X/Ds +/^abc\00def/I + abc\00def\L\C0 -/(.*X|^B)/D +/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)?)?)?)?)?)?)?)?)?otherword/I -/(.*X|^B)/Ds - -/(?s)(.*X|^B)/D +/.*X/IDZ + +/.*X/IDZs + +/(.*X|^B)/IDZ + +/(.*X|^B)/IDZs + +/(?s)(.*X|^B)/IDZ -/(?s:.*X|^B)/D +/(?s:.*X|^B)/IDZ -/\Biss\B/+ +/\Biss\B/I+ Mississippi -/\Biss\B/+P +/\Biss\B/I+P Mississippi -/iss/G+ +/iss/IG+ Mississippi -/\Biss\B/G+ +/\Biss\B/IG+ Mississippi -/\Biss\B/g+ +/\Biss\B/Ig+ Mississippi *** Failers Mississippi\A -/(?<=[Ms])iss/g+ +/(?<=[Ms])iss/Ig+ Mississippi -/(?<=[Ms])iss/G+ +/(?<=[Ms])iss/IG+ Mississippi -/^iss/g+ +/^iss/Ig+ ississippi - -/.*iss/g+ - abciss\nxyzisspqr -/.i./+g +/.*iss/Ig+ + abciss\nxyzisspqr + +/.i./I+g Mississippi Mississippi\A Missouri river - Missouri river\A + Missouri river\A -/^.is/+g +/^.is/I+g Mississippi -/^ab\n/g+ +/^ab\n/Ig+ ab\nab\ncd -/^ab\n/mg+ +/^ab\n/Img+ ab\nab\ncd -/abc/ +/abc/I -/abc|bac/ +/abc|bac/I -/(abc|bac)/ +/(abc|bac)/I -/(abc|(c|dc))/ +/(abc|(c|dc))/I -/(abc|(d|de)c)/ +/(abc|(d|de)c)/I -/a*/ +/a*/I -/a+/ +/a+/I -/(baa|a+)/ +/(baa|a+)/I -/a{0,3}/ +/a{0,3}/I -/baa{3,}/ +/baa{3,}/I -/"([^\\"]+|\\.)*"/ +/"([^\\"]+|\\.)*"/I -/(abc|ab[cd])/ +/(abc|ab[cd])/I -/(a|.)/ +/(a|.)/I -/a|ba|\w/ +/a|ba|\w/I -/abc(?=pqr)/ +/abc(?=pqr)/I -/...(?<=abc)/ +/...(?<=abc)/I -/abc(?!pqr)/ +/abc(?!pqr)/I -/ab./ +/ab./I -/ab[xyz]/ +/ab[xyz]/I -/abc*/ +/abc*/I -/ab.c*/ +/ab.c*/I -/a.c*/ +/a.c*/I -/.c*/ +/.c*/I -/ac*/ +/ac*/I -/(a.c*|b.c*)/ +/(a.c*|b.c*)/I -/a.c*|aba/ +/a.c*|aba/I -/.+a/ +/.+a/I -/(?=abcda)a.*/ +/(?=abcda)a.*/I -/(?=a)a.*/ +/(?=a)a.*/I -/a(b)*/ +/a(b)*/I -/a\d*/ +/a\d*/I -/ab\d*/ +/ab\d*/I -/a(\d)*/ +/a(\d)*/I -/abcde{0,0}/ +/abcde{0,0}/I -/ab\d+/ +/ab\d+/I -/a(?(1)b)/ +/a(?(1)b)(.)/I -/a(?(1)bag|big)/ +/a(?(1)bag|big)(.)/I -/a(?(1)bag|big)*/ +/a(?(1)bag|big)*(.)/I -/a(?(1)bag|big)+/ +/a(?(1)bag|big)+(.)/I -/a(?(1)b..|b..)/ +/a(?(1)b..|b..)(.)/I -/ab\d{0}e/ +/ab\d{0}e/I -/a?b?/ +/a?b?/I a b ab \ *** Failers - \N - -/|-/ + \N + +/|-/I abcd -abc \Nab-c *** Failers - \Nabc + \Nabc -/a*(b+)(z)(z)/P +/a*(b+)(z)(z)/IP aaaabbbbzzzz aaaabbbbzzzz\O0 aaaabbbbzzzz\O1 @@ -601,8 +601,8 @@ aaaabbbbzzzz\O3 aaaabbbbzzzz\O4 aaaabbbbzzzz\O5 - -/^.?abcd/S + +/^.?abcd/IS /\( # ( at start (?: # Non-capturing bracket @@ -611,343 +611,343 @@ (?R) # Recurse - i.e. nested bracketed string )* # Zero or more contents \) # Closing ) - /x + /Ix (abcd) (abcd)xyz xyz(abcd) - (ab(xy)cd)pqr - (ab(xycd)pqr - () abc () + (ab(xy)cd)pqr + (ab(xycd)pqr + () abc () 12(abcde(fsh)xyz(foo(bar))lmno)89 *** Failers - abcd + abcd abcd) - (abcd + (abcd -/\( ( (?>[^()]+) | (?R) )* \) /xg - (ab(xy)cd)pqr +/\( ( (?>[^()]+) | (?R) )* \) /Ixg + (ab(xy)cd)pqr 1(abcd)(x(y)z)pqr -/\( (?: (?>[^()]+) | (?R) ) \) /x +/\( (?: (?>[^()]+) | (?R) ) \) /Ix (abcd) (ab(xy)cd) - (a(b(c)d)e) - ((ab)) + (a(b(c)d)e) + ((ab)) *** Failers - () + () -/\( (?: (?>[^()]+) | (?R) )? \) /x +/\( (?: (?>[^()]+) | (?R) )? \) /Ix () 12(abcde(fsh)xyz(foo(bar))lmno)89 -/\( ( (?>[^()]+) | (?R) )* \) /x +/\( ( (?>[^()]+) | (?R) )* \) /Ix (ab(xy)cd) -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x +/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix (ab(xy)cd) -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix (ab(xy)cd) (123ab(xy)cd) -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix (ab(xy)cd) (123ab(xy)cd) -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix (ab(xy)cd) -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix (abcd(xyz<p>qrs)123) -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix (ab(cd)ef) (ab(cd(ef)gh)ij) -/^[[:alnum:]]/D +/^[[:alnum:]]/DZ -/^[[:^alnum:]]/D +/^[[:^alnum:]]/DZ -/^[[:alpha:]]/D +/^[[:alpha:]]/DZ + +/^[[:^alpha:]]/DZ -/^[[:^alpha:]]/D - /[_[:alpha:]]/IS -/^[[:ascii:]]/D +/^[[:ascii:]]/DZ -/^[[:^ascii:]]/D +/^[[:^ascii:]]/DZ -/^[[:blank:]]/D +/^[[:blank:]]/DZ -/^[[:^blank:]]/D +/^[[:^blank:]]/DZ /[\n\x0b\x0c\x0d[:blank:]]/IS -/^[[:cntrl:]]/D +/^[[:cntrl:]]/DZ -/^[[:digit:]]/D +/^[[:digit:]]/DZ -/^[[:graph:]]/D +/^[[:graph:]]/DZ -/^[[:lower:]]/D +/^[[:lower:]]/DZ -/^[[:print:]]/D +/^[[:print:]]/DZ -/^[[:punct:]]/D +/^[[:punct:]]/DZ -/^[[:space:]]/D +/^[[:space:]]/DZ -/^[[:upper:]]/D +/^[[:upper:]]/DZ -/^[[:xdigit:]]/D +/^[[:xdigit:]]/DZ -/^[[:word:]]/D +/^[[:word:]]/DZ -/^[[:^cntrl:]]/D +/^[[:^cntrl:]]/DZ -/^[12[:^digit:]]/D +/^[12[:^digit:]]/DZ -/^[[:^blank:]]/D +/^[[:^blank:]]/DZ -/[01[:alpha:]%]/D +/[01[:alpha:]%]/DZ -/[[.ch.]]/ +/[[.ch.]]/I -/[[=ch=]]/ +/[[=ch=]]/I -/[[:rhubarb:]]/ +/[[:rhubarb:]]/I -/[[:upper:]]/i +/[[:upper:]]/Ii A - a - -/[[:lower:]]/i + a + +/[[:lower:]]/Ii A - a + a -/((?-i)[[:lower:]])[[:lower:]]/i +/((?-i)[[:lower:]])[[:lower:]]/Ii ab aB *** Failers Ab - AB + AB -/[\200-\110]/ +/[\200-\110]/I -/^(?(0)f|b)oo/ +/^(?(0)f|b)oo/I -/This one's here because of the large output vector needed/ +/This one's here because of the large output vector needed/I -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC -/This one's here because Perl does this differently and PCRE can't at present/ +/This one's here because Perl does this differently and PCRE can't at present/I -/(main(O)?)+/ +/(main(O)?)+/I mainmain mainOmain - -/These are all cases where Perl does it differently (nested captures)/ -/^(a(b)?)+$/ +/These are all cases where Perl does it differently (nested captures)/I + +/^(a(b)?)+$/I aba - -/^(aa(bb)?)+$/ - aabbaa - -/^(aa|aa(bb))+$/ - aabbaa - -/^(aa(bb)??)+$/ - aabbaa - -/^(?:aa(bb)?)+$/ - aabbaa - -/^(aa(b(b))?)+$/ - aabbaa -/^(?:aa(b(b))?)+$/ - aabbaa +/^(aa(bb)?)+$/I + aabbaa -/^(?:aa(b(?:b))?)+$/ - aabbaa +/^(aa|aa(bb))+$/I + aabbaa -/^(?:aa(bb(?:b))?)+$/ - aabbbaa - -/^(?:aa(b(?:bb))?)+$/ - aabbbaa +/^(aa(bb)??)+$/I + aabbaa -/^(?:aa(?:b(b))?)+$/ - aabbaa +/^(?:aa(bb)?)+$/I + aabbaa -/^(?:aa(?:b(bb))?)+$/ - aabbbaa +/^(aa(b(b))?)+$/I + aabbaa -/^(aa(b(bb))?)+$/ - aabbbaa +/^(?:aa(b(b))?)+$/I + aabbaa -/^(aa(bb(bb))?)+$/ - aabbbbaa +/^(?:aa(b(?:b))?)+$/I + aabbaa -/--------------------------------------------------------------------/ - -/#/xMD +/^(?:aa(bb(?:b))?)+$/I + aabbbaa + +/^(?:aa(b(?:bb))?)+$/I + aabbbaa + +/^(?:aa(?:b(b))?)+$/I + aabbaa -/a#/xMD +/^(?:aa(?:b(bb))?)+$/I + aabbbaa -/[\s]/D +/^(aa(b(bb))?)+$/I + aabbbaa -/[\S]/D +/^(aa(bb(bb))?)+$/I + aabbbbaa -/a(?i)b/D +/--------------------------------------------------------------------/I + +/#/IxDZ + +/a#/IxDZ + +/[\s]/DZ + +/[\S]/DZ + +/a(?i)b/DZ ab aB - *** Failers - AB + *** Failers + AB -/(a(?i)b)/D +/(a(?i)b)/DZ ab aB - *** Failers - AB - -/ (?i)abc/xD + *** Failers + AB + +/ (?i)abc/IxDZ /#this is a comment - (?i)abc/xD + (?i)abc/IxDZ -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ -/\Q\E/D +/\Q\E/DZ \ -/\Q\Ex/D +/\Q\Ex/DZ -/ \Q\E/D +/ \Q\E/DZ -/a\Q\E/D +/a\Q\E/DZ abc bca - bac + bac -/a\Q\Eb/D +/a\Q\Eb/DZ abc -/\Q\Eabc/D +/\Q\Eabc/DZ -/x*+\w/D +/x*+\w/DZ *** Failers xxxxx - -/x?+/D -/x++/D +/x?+/DZ -/x{1,3}+/D +/x++/DZ -/(x)*+/D +/x{1,3}+/DZ -/^(\w++|\s++)*$/ +/(x)*+/DZ + +/^(\w++|\s++)*$/I now is the time for all good men to come to the aid of the party *** Failers this is not a line with only words and spaces! - -/(\d++)(\w)/ + +/(\d++)(\w)/I 12345a *** Failers - 12345+ + 12345+ -/a++b/ +/a++b/I aaab -/(a++b)/ +/(a++b)/I aaab -/(a++)b/ +/(a++)b/I aaab -/([^()]++|\([^()]*\))+/ +/([^()]++|\([^()]*\))+/I ((abc(ade)ufh()()x - -/\(([^()]++|\([^()]+\))+\)/ + +/\(([^()]++|\([^()]+\))+\)/I (abc) (abc(def)xyz) *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -/(abc){1,3}+/D +/(abc){1,3}+/DZ -/a+?+/ +/a+?+/I -/a{2,3}?+b/ +/a{2,3}?+b/I -/(?U)a+?+/ +/(?U)a+?+/I -/a{2,3}?+b/U +/a{2,3}?+b/IU -/x(?U)a++b/D +/x(?U)a++b/DZ xaaaab -/(?U)xa++b/D +/(?U)xa++b/DZ xaaaab -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ -/^x(?U)a+b/D +/^x(?U)a+b/DZ -/^x(?U)(a+)b/D +/^x(?U)(a+)b/DZ -/[.x.]/ +/[.x.]/I -/[=x=]/ +/[=x=]/I -/[:x:]/ +/[:x:]/I -/\l/ +/\l/I -/\L/ +/\L/I -/\N{name}/ +/\N{name}/I -/\u/ +/\u/I -/\U/ +/\U/I -/[/ +/[/I -/[a-/ +/[a-/I -/[[:space:]/ +/[[:space:]/I -/[\s]/DM +/[\s]/IDZ -/[[:space:]]/DM +/[[:space:]]/IDZ -/[[:space:]abcde]/DM +/[[:space:]abcde]/IDZ -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix <> <abcd> <abc <123> hij> <abc <def> hij> - <abc<>def> - <abc<> + <abc<>def> + <abc<> *** Failers <abc -|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM +|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ /(.*)\d+\1/I /(.*)\d+/I - + /(.*)\d+\1/Is /(.*)\d+/Is @@ -956,12 +956,12 @@ /((.*))\d+\1/I abc123bc - + /a[b]/I /(?=a).*/I -/(?=abc).xyz/iI +/(?=abc).xyz/IiI /(?=abc)(?i).xyz/I @@ -975,13 +975,13 @@ /()a/I -/(?(1)ab|ac)/I +/(?(1)ab|ac)(.)/I -/(?(1)abz|acz)/I +/(?(1)abz|acz)(.)/I -/(?(1)abz)/I +/(?(1)abz)(.)/I -/(?(1)abz)123/I +/(?(1)abz)(1)23/I /(a)+/I @@ -1003,11 +1003,11 @@ /a^b/I -/^a/mI +/^a/Im abcde - xy\nabc - *** Failers - xyabc + xy\nabc + *** Failers + xyabc /c|abc/I @@ -1015,328 +1015,328 @@ /[ab](?i)cd/IS -/abc(?C)def/ +/abc(?C)def/I abcdef - 1234abcdef + 1234abcdef *** Failers abcxyz - abcxyzf + abcxyzf -/abc(?C)de(?C1)f/ +/abc(?C)de(?C1)f/I 123abcdef - -/(?C1)\dabc(?C2)def/ + +/(?C1)\dabc(?C2)def/I 1234abcdef *** Failers - abcdef - -/(?C255)ab/ + abcdef -/(?C256)ab/ +/(?C255)ab/I -/(?Cab)xx/ +/(?C256)ab/I -/(?C12vr)x/ +/(?Cab)xx/I -/abc(?C)def/ +/(?C12vr)x/I + +/abc(?C)def/I *** Failers \x83\x0\x61bcdef -/(abc)(?C)de(?C1)f/ +/(abc)(?C)de(?C1)f/I 123abcdef - 123abcdef\C+ - 123abcdef\C- + 123abcdef\C+ + 123abcdef\C- *** Failers - 123abcdef\C!1 - -/(?C0)(abc(?C1))*/ + 123abcdef\C!1 + +/(?C0)(abc(?C1))*/I abcabcabc - abcabc\C!1!3 + abcabc\C!1!3 *** Failers - abcabcabc\C!1!3 + abcabcabc\C!1!3 -/(\d{3}(?C))*/ +/(\d{3}(?C))*/I 123\C+ 123456\C+ - 123456789\C+ + 123456789\C+ -/((xyz)(?C)p|(?C1)xyzabc)/ +/((xyz)(?C)p|(?C1)xyzabc)/I xyzabc\C+ -/(X)((xyz)(?C)p|(?C1)xyzabc)/ +/(X)((xyz)(?C)p|(?C1)xyzabc)/I Xxyzabc\C+ -/(?=(abc))(?C)abcdef/ +/(?=(abc))(?C)abcdef/I abcdef\C+ - -/(?!(abc)(?C1)d)(?C2)abcxyz/ - abcxyz\C+ -/(?<=(abc)(?C))xyz/ +/(?!(abc)(?C1)d)(?C2)abcxyz/I + abcxyz\C+ + +/(?<=(abc)(?C))xyz/I abcxyz\C+ - -/a(b+)(c*)(?C1)/ + +/a(b+)(c*)(?C1)/I abbbbbccc\C*1 -/a(b+?)(c*?)(?C1)/ +/a(b+?)(c*?)(?C1)/I abbbbbccc\C*1 - -/(?C)abc/ -/(?C)^abc/ +/(?C)abc/I -/(?C)a|b/S +/(?C)^abc/I -/(?R)/ +/(?C)a|b/IS -/(a|(?R))/ +/(?R)/I -/(ab|(bc|(de|(?R))))/ +/(a|(?R))/I -/x(ab|(bc|(de|(?R))))/ +/(ab|(bc|(de|(?R))))/I + +/x(ab|(bc|(de|(?R))))/I xab xbc xde xxab xxxab *** Failers - xyab + xyab -/(ab|(bc|(de|(?1))))/ +/(ab|(bc|(de|(?1))))/I -/x(ab|(bc|(de|(?1)x)x)x)/ +/x(ab|(bc|(de|(?1)x)x)x)/I -/^([^()]|\((?1)*\))*$/ +/^([^()]|\((?1)*\))*$/I abc a(b)c - a(b(c))d + a(b(c))d *** Failers) - a(b(c)d + a(b(c)d -/^>abc>([^()]|\((?1)*\))*<xyz<$/ +/^>abc>([^()]|\((?1)*\))*<xyz<$/I >abc>123<xyz< >abc>1(2)3<xyz< >abc>(1(2)3)<xyz< -/(a(?1)b)/D +/(a(?1)b)/DZ -/(a(?1)+b)/D +/(a(?1)+b)/DZ -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/i +/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/Ii 1221 Satan, oscillate my metallic sonatas! A man, a plan, a canal: Panama! - Able was I ere I saw Elba. + Able was I ere I saw Elba. *** Failers - The quick brown fox - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ + The quick brown fox + +/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I 12 (((2+2)*-3)-7) -12 *** Failers ((2+2)*-3)-7) - -/^(x(y|(?1){2})z)/ + +/^(x(y|(?1){2})z)/I xyz - xxyzxyzz + xxyzxyzz *** Failers xxyzz - xxyzxyzxyzz + xxyzxyzxyzz -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x +/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix <> <abcd> <abc <123> hij> <abc <def> hij> - <abc<>def> - <abc<> + <abc<>def> + <abc<> *** Failers <abc -/(?1)/ +/(?1)/I -/((?2)(abc)/ +/((?2)(abc)/I -/^(abc)def(?1)/ +/^(abc)def(?1)/I abcdefabc -/^(a|b|c)=(?1)+/ +/^(a|b|c)=(?1)+/I a=a a=b - a=bc + a=bc -/^(a|b|c)=((?1))+/ +/^(a|b|c)=((?1))+/I a=a a=b - a=bc + a=bc -/a(?P<name1>b|c)d(?P<longername2>e)/D +/a(?P<name1>b|c)d(?P<longername2>e)/DZ abde - acde + acde -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/D +/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/DZ -/(?P<a>a)...(?P=a)bbb(?P>a)d/D +/(?P<a>a)...(?P=a)bbb(?P>a)d/DZ -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i +/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii 1221 Satan, oscillate my metallic sonatas! A man, a plan, a canal: Panama! - Able was I ere I saw Elba. + Able was I ere I saw Elba. *** Failers - The quick brown fox - -/((?(R)a|b))\1(?1)?/ + The quick brown fox + +/((?(R)a|b))\1(?1)?/I bb - bbaa + bbaa -/(.*)a/sI +/(.*)a/Is -/(.*)a\1/sI +/(.*)a\1/Is -/(.*)a(b)\2/sI +/(.*)a(b)\2/Is -/((.*)a|(.*)b)z/sI +/((.*)a|(.*)b)z/Is -/((.*)a|(.*)b)z\1/sI +/((.*)a|(.*)b)z\1/Is -/((.*)a|(.*)b)z\2/sI +/((.*)a|(.*)b)z\2/Is -/((.*)a|(.*)b)z\3/sI +/((.*)a|(.*)b)z\3/Is -/((.*)a|^(.*)b)z\3/sI +/((.*)a|^(.*)b)z\3/Is -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is -/(a)(bc)/ND +/(a)(bc)/INDZ abc -/(?P<one>a)(bc)/ND +/(?P<one>a)(bc)/INDZ abc -/(a)(?P<named>bc)/ND +/(a)(?P<named>bc)/INDZ -/(a+)*zz/ +/(a+)*zz/I aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M aaaaaaaaaaaaaz\M -/(aaa(?C1)bbb|ab)/ +/(aaa(?C1)bbb|ab)/I aaabbb aaabbb\C*0 aaabbb\C*1 aaabbb\C*-1 -/ab(?P<one>cd)ef(?P<two>gh)/ +/ab(?P<one>cd)ef(?P<two>gh)/I abcdefgh abcdefgh\C1\Gtwo abcdefgh\Cone\Ctwo - abcdefgh\Cthree + abcdefgh\Cthree -/(?P<Tes>)(?P<Test>)/D +/(?P<Tes>)(?P<Test>)/DZ -/(?P<Test>)(?P<Tes>)/D +/(?P<Test>)(?P<Tes>)/DZ -/(?P<Z>zz)(?P<A>aa)/ +/(?P<Z>zz)(?P<A>aa)/I zzaa\CZ zzaa\CA -/(?P<x>eks)(?P<x>eccs)/ +/(?P<x>eks)(?P<x>eccs)/I -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ +/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/I -"\[((?P<elem>\d+)(,(?P>elem))*)\]" +"\[((?P<elem>\d+)(,(?P>elem))*)\]"I [10,20,30,5,5,4,4,2,43,23,4234] *** Failers - [] + [] -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" +"\[((?P<elem>\d+)(,(?P>elem))*)?\]"I [10,20,30,5,5,4,4,2,43,23,4234] - [] + [] -/(a(b(?2)c))?/D +/(a(b(?2)c))?/DZ -/(a(b(?2)c))*/D +/(a(b(?2)c))*/DZ -/(a(b(?2)c)){0,2}/D +/(a(b(?2)c)){0,2}/DZ -/[ab]{1}+/D +/[ab]{1}+/DZ -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii Baby Bjorn Active Carrier - With free SHIPPING!! -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/SD -/(a|b)*.?c/SD +/a*.*b/ISDZ + +/(a|b)*.?c/ISDZ -/abc(?C255)de(?C)f/D +/abc(?C255)de(?C)f/DZ -/abcde/CD +/abcde/ICDZ abcde - abcdfe - -/a*b/CD + abcdfe + +/a*b/ICDZ ab aaaab - aaaacb + aaaacb -/a+b/CD +/a+b/ICDZ ab aaaab - aaaacb + aaaacb -/(abc|def)x/CD +/(abc|def)x/ICDZ abcx defx abcdefzx -/(ab|cd){3,4}/C +/(ab|cd){3,4}/IC ababab abcdabcd - abcdcdcdcdcd + abcdcdcdcdcd -/([ab]{,4}c|xy)/CD +/([ab]{,4}c|xy)/ICDZ Note: that { does NOT introduce a quantifier -/([ab]{1,4}c|xy){4,5}?123/CD +/([ab]{1,4}c|xy){4,5}?123/ICDZ aacaacaacaacaac123 /\b.*/I ab cd\>1 - -/\b.*/Is + +/\b.*/Is ab cd\>1 - + /(?!.bcd).*/I - Xbcd12345 + Xbcd12345 -/abcde/ +/abcde/I ab\P abc\P abcd\P - abcde\P + abcde\P the quick brown abc\P ** Failers\P the quick brown abxyz fox\P - -"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$" + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I 13/05/04\P 13/5/2004\P - 02/05/09\P + 02/05/09\P 1\P 1/2\P 1/2/0\P - 1/2/04\P + 1/2/04\P 0\P 02/\P - 02/0\P + 02/0\P 02/1\P ** Failers\P \P @@ -1344,285 +1344,285 @@ 33/4/04\P 3/13/04\P 0/1/2003\P - 0/\P - 02/0/\P - 02/13\P + 0/\P + 02/0/\P + 02/13\P /0{0,2}ABC/I - + /\d{3,}ABC/I - + /\d*ABC/I /[abc]+DE/I -/[abc]?123/ +/[abc]?123/I 123\P a\P b\P c\P c12\P - c123\P + c123\P -/^(?:\d){3,5}X/ +/^(?:\d){3,5}X/I 1\P 123\P 123X 1234\P 1234X 12345\P - 12345X - *** Failers - 1X - 123456\P + 12345X + *** Failers + 1X + 123456\P -/abc/>testsavedregex +/abc/I>testsavedregex <testsavedregex abc ** Failers bca - -/abc/F>testsavedregex + +/abc/IF>testsavedregex <testsavedregex abc ** Failers bca -/(a|b)/S>testsavedregex +/(a|b)/IS>testsavedregex <testsavedregex abc ** Failers - def - -/(a|b)/SF>testsavedregex + def + +/(a|b)/ISF>testsavedregex <testsavedregex abc ** Failers - def - -~<(\w+)/?>(.)*</(\1)>~smg + def + +~<(\w+)/?>(.)*</(\1)>~smgI <!DOCTYPE seite SYSTEM "http://www.lco.lineas.de/xmlCms.dtd">\n<seite>\n<dokumenteninformation>\n<seitentitel>Partner der LCO</seitentitel>\n<sprache>de</sprache>\n<seitenbeschreibung>Partner der LINEAS Consulting\nGmbH</seitenbeschreibung>\n<schluesselworte>LINEAS Consulting GmbH Hamburg\nPartnerfirmen</schluesselworte>\n<revisit>30 days</revisit>\n<robots>index,follow</robots>\n<menueinformation>\n<aktiv>ja</aktiv>\n<menueposition>3</menueposition>\n<menuetext>Partner</menuetext>\n</menueinformation>\n<lastedited>\n<autor>LCO</autor>\n<firma>LINEAS Consulting</firma>\n<datum>15.10.2003</datum>\n</lastedited>\n</dokumenteninformation>\n<inhalt>\n\n<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\nGmbH</absatzueberschrift>\n\n<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\n<bild name="logo_ca.gif" rahmen="no"/></link> <link\nziel="http://www.ey.com/" zielfenster="_blank"><bild\nname="logo_euy.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\n<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\n\n<absatz><link ziel="http://www.atelion.de/"\nzielfenster="_blank"><bild\nname="logo_atelion.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.line-information.de/"\nzielfenster="_blank">\n<bild name="logo_line_information.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\n\n<absatz><link ziel="http://www.incognis.de/"\nzielfenster="_blank"><bild\nname="logo_incognis.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.addcraft.com/"\nzielfenster="_blank"><bild\nname="logo_addcraft.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.comendo.com/"\nzielfenster="_blank"><bild\nname="logo_comendo.gif" rahmen="no"/></link></absatz>\n\n</inhalt>\n</seite> /^a/IF -/line\nbreak/ +/line\nbreak/I this is a line\nbreak - line one\nthis is a line\nbreak in the second line + line one\nthis is a line\nbreak in the second line -/line\nbreak/f +/line\nbreak/If this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line + ** Failers + line one\nthis is a line\nbreak in the second line -/line\nbreak/mf +/line\nbreak/Imf this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line + ** Failers + line one\nthis is a line\nbreak in the second line -/ab.cd/P +/ab.cd/IP ab-cd - ab=cd + ab=cd ** Failers ab\ncd -/ab.cd/Ps +/ab.cd/IPs ab-cd - ab=cd + ab=cd ab\ncd -/(?i)(?-i)AbCd/ +/(?i)(?-i)AbCd/I AbCd ** Failers - abcd - -/a{11111111111111111111}/ + abcd -/(){64294967295}/ +/a{11111111111111111111}/I -/(){2,4294967295}/ +/(){64294967295}/I -"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B" +/(){2,4294967295}/I + +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I abcdefghijklAkB -"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B" +"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I abcdefghijklAkB -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B" +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I abcdefghijklAkB -"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)" +"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)" +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -/[^()]*(?:\((?R)\)[^()]*)*/ +/[^()]*(?:\((?R)\)[^()]*)*/I (this(and)that - (this(and)that) + (this(and)that) (this(and)that)stuff -/[^()]*(?:\((?>(?R))\)[^()]*)*/ +/[^()]*(?:\((?>(?R))\)[^()]*)*/I (this(and)that - (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/ + (this(and)that) + +/[^()]*(?:\((?R)\))*[^()]*/I (this(and)that - (this(and)that) + (this(and)that) -/(?:\((?R)\))*[^()]*/ +/(?:\((?R)\))*[^()]*/I (this(and)that - (this(and)that) - ((this)) + (this(and)that) + ((this)) -/(?:\((?R)\))|[^()]*/ +/(?:\((?R)\))|[^()]*/I (this(and)that - (this(and)that) + (this(and)that) (this) - ((this)) - -/a(b)c/PN + ((this)) + +/a(b)c/IPN abc - -/a(?P<name>b)c/PN - abc - -/\x{100}/ -/\x{0000ff}/ +/a(?P<name>b)c/IPN + abc + +/\x{100}/I + +/\x{0000ff}/I -/^((?P<A>a1)|(?P<A>a2)b)/ +/^((?P<A>a1)|(?P<A>a2)b)/I -/^((?P<A>a1)|(?P<A>a2)b)/J +/^((?P<A>a1)|(?P<A>a2)b)/IJ a1b\CA - a2b\CA + a2b\CA ** Failers - a1b\CZ\CA - -/^(?P<A>a)(?P<A>b)/J + a1b\CZ\CA + +/^(?P<A>a)(?P<A>b)/IJ ab\CA - -/^(?P<A>a)(?P<A>b)|cd/J + +/^(?P<A>a)(?P<A>b)|cd/IJ ab\CA - cd\CA - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J - cdefgh\CA - -/^((?P<A>a1)|(?P<A>a2)b)/J + cd\CA + +/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ + cdefgh\CA + +/^((?P<A>a1)|(?P<A>a2)b)/IJ a1b\GA - a2b\GA + a2b\GA ** Failers - a1b\GZ\GA - -/^(?P<A>a)(?P<A>b)/J + a1b\GZ\GA + +/^(?P<A>a)(?P<A>b)/IJ ab\GA - -/^(?P<A>a)(?P<A>b)|cd/J + +/^(?P<A>a)(?P<A>b)|cd/IJ ab\GA - cd\GA - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J - cdefgh\GA - -/(?J)^((?P<A>a1)|(?P<A>a2)b)/ + cd\GA + +/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ + cdefgh\GA + +/(?J)^((?P<A>a1)|(?P<A>a2)b)/I a1b\CA - a2b\CA - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/ + a2b\CA + +/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/I / In this next test, J is not set at the outer level; consequently it isn't -set in the pattern's options; consequently pcre_get_named_substring() produces -a random value. /x +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /Ix -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/ +/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I a bc d\CA\CB\CC -/^(?P<A>a)?(?(A)a|b)/ +/^(?P<A>a)?(?(A)a|b)/I aabc bc ** Failers - abc + abc -/(?:(?(ZZ)a|b)(?P<ZZ>X))+/ +/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I bXaX -/(?:(?(2y)a|b)(X))+/ +/(?:(?(2y)a|b)(X))+/I -/(?:(?(ZA)a|b)(?P<ZZ>X))+/ +/(?:(?(ZA)a|b)(?P<ZZ>X))+/I -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/ +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I bbXaaX -/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/ +/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I (b)\\Xa\\X -/(?P<ABC/ +/(?P<ABC/I -/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ +/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I bXXaYYaY - bXYaXXaX + bXYaXXaX -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I bXXaYYaY -/\777/ +/\777/I -/\s*,\s*/S +/\s*,\s*/IS \x0b,\x0b - \x0c,\x0d + \x0c,\x0d -/^abc/m +/^abc/Im xyz\nabc xyz\nabc\<lf> xyz\r\nabc\<lf> xyz\rabc\<cr> xyz\r\nabc\<crlf> - ** Failers + ** Failers xyz\nabc\<cr> xyz\r\nabc\<cr> xyz\nabc\<crlf> xyz\rabc\<crlf> xyz\rabc\<lf> - -/abc$/m + +/abc$/Im<lf> xyzabc - xyzabc\n - xyzabc\npqr - xyzabc\r\<cr> - xyzabc\rpqr\<cr> - xyzabc\r\n\<crlf> - xyzabc\r\npqr\<crlf> - ** Failers - xyzabc\r - xyzabc\rpqr - xyzabc\r\n - xyzabc\r\npqr - -/^abc/m<cr> + xyzabc\n + xyzabc\npqr + xyzabc\r\<cr> + xyzabc\rpqr\<cr> + xyzabc\r\n\<crlf> + xyzabc\r\npqr\<crlf> + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/Im<cr> xyz\rabcdef xyz\nabcdef\<lf> - ** Failers + ** Failers xyz\nabcdef - -/^abc/m<lf> + +/^abc/Im<lf> xyz\nabcdef xyz\rabcdef\<cr> - ** Failers + ** Failers xyz\rabcdef - -/^abc/m<crlf> + +/^abc/Im<crlf> xyz\r\nabcdef xyz\rabcdef\<cr> - ** Failers + ** Failers xyz\rabcdef - -/^abc/m<bad> -/abc/ +/^abc/Im<bad> + +/abc/I xyz\rabc\<bad> - abc - -/.*/ + abc + +/.*/I<lf> abc\ndef abc\rdef abc\r\ndef @@ -1633,14 +1633,1144 @@ \<crlf>abc\rdef \<crlf>abc\r\ndef -/\w+(.)(.)?def/s +/\w+(.)(.)?def/Is abc\ndef abc\rdef abc\r\ndef -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+ ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I /* this is a C style comment */\M -/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/ +/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I + +/()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + (.(.))/Ix + XY\O400 + +/(a*b|(?i:c*(?-i)d))/IS + +/()[ab]xyz/IS + +/(|)[ab]xyz/IS + +/(|c)[ab]xyz/IS + +/(|c?)[ab]xyz/IS + +/(d?|c?)[ab]xyz/IS + +/(d?|c)[ab]xyz/IS + +/^a*b\d/DZ + +/^a*+b\d/DZ + +/^a*?b\d/DZ + +/^a+A\d/DZ + aaaA5 + ** Failers + aaaa5 + +/^a*A\d/IiDZ + aaaA5 + aaaa5 + +/(a*|b*)[cd]/IS + +/(a+|b*)[cd]/IS + +/(a*|b+)[cd]/IS + +/(a+|b+)[cd]/IS + +/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + ((( + a + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + ))) +/Ix + large nest + +/a*\d/BZ + +/a*\D/BZ + +/0*\d/BZ + +/0*\D/BZ + +/a*\s/BZ + +/a*\S/BZ + +/ *\s/BZ + +/ *\S/BZ + +/a*\w/BZ + +/a*\W/BZ + +/=*\w/BZ + +/=*\W/BZ + +/\d*a/BZ + +/\d*2/BZ + +/\d*\d/BZ + +/\d*\D/BZ + +/\d*\s/BZ + +/\d*\S/BZ + +/\d*\w/BZ + +/\d*\W/BZ + +/\D*a/BZ + +/\D*2/BZ + +/\D*\d/BZ + +/\D*\D/BZ + +/\D*\s/BZ + +/\D*\S/BZ + +/\D*\w/BZ + +/\D*\W/BZ + +/\s*a/BZ + +/\s*2/BZ + +/\s*\d/BZ + +/\s*\D/BZ + +/\s*\s/BZ + +/\s*\S/BZ + +/\s*\w/BZ + +/\s*\W/BZ + +/\S*a/BZ + +/\S*2/BZ + +/\S*\d/BZ + +/\S*\D/BZ + +/\S*\s/BZ + +/\S*\S/BZ + +/\S*\w/BZ + +/\S*\W/BZ + +/\w*a/BZ + +/\w*2/BZ + +/\w*\d/BZ + +/\w*\D/BZ + +/\w*\s/BZ + +/\w*\S/BZ + +/\w*\w/BZ + +/\w*\W/BZ + +/\W*a/BZ + +/\W*2/BZ + +/\W*\d/BZ + +/\W*\D/BZ + +/\W*\s/BZ + +/\W*\S/BZ + +/\W*\w/BZ + +/\W*\W/BZ + +/[^a]+a/BZ + +/[^a]+a/BZi + +/[^a]+A/BZi + +/[^a]+b/BZ + +/[^a]+\d/BZ + +/a*[^a]/BZ + +/(?P<abc>x)(?P<xyz>y)/I + xy\Cabc\Cxyz + +/(?<abc>x)(?'xyz'y)/I + xy\Cabc\Cxyz + +/(?<abc'x)(?'xyz'y)/I + +/(?<abc>x)(?'xyz>y)/I + +/(?P'abc'x)(?P<xyz>y)/I + +/^(?:(?(ZZ)a|b)(?<ZZ>X))+/ + bXaX + bXbX + ** Failers + aXaX + aXbX + +/^(?P>abc)(?<abcd>xxx)/ + +/^(?P>abc)(?<abc>x|y)/ + xx + xy + yy + yx + +/^(?P>abc)(?P<abc>x|y)/ + xx + xy + yy + yx + +/^((?(abc)a|b)(?<abc>x|y))+/ + bxay + bxby + ** Failers + axby + +/^(((?P=abc)|X)(?<abc>x|y))+/ + XxXxxx + XxXyyx + XxXyxx + ** Failers + x + +/^(?1)(abc)/ + abcabc + +/^(?:(?:\1|X)(a|b))+/ + Xaaa + Xaba + +/^[\E\Qa\E-\Qz\E]+/BZ + +/^[a\Q]bc\E]/BZ + +/^[a-\Q\E]/BZ + +/^(?P>abc)[()](?<abc>)/BZ + +/^((?(abc)y)[()](?P<abc>x))+/BZ + (xy)x + +/^(?P>abc)\Q()\E(?<abc>)/BZ + +/^(?P>abc)[a\Q(]\E(](?<abc>)/BZ + +/^(?P>abc) # this is (a comment) + (?<abc>)/BZx + +/^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii + 1221 + Satan, oscillate my metallic sonatas! + A man, a plan, a canal: Panama! + Able was I ere I saw Elba. + *** Failers + The quick brown fox + +/(?=(\w+))\1:/I + abcd: + +/(?=(?'abc'\w+))\k<abc>:/I + abcd: + +/(?'abc'\w+):\k<abc>{2}/ + a:aaxyz + ab:ababxyz + ** Failers + a:axyz + ab:abxyz + +/(?'abc'a|b)(?<abc>d|e)\k<abc>{2}/J + adaa + ** Failers + addd + adbb + +/(?'abc'a|b)(?<abc>d|e)(?&abc){2}/J + bdaa + bdab + ** Failers + bddd + +/^(?<ab>a)? (?(<ab>)b|c) (?('ab')d|e)/x + abd + ce + +/(?(<bc))/ + +/(?(''))/ + +/(?('R')stuff)/ + +/((abc (?(R) (?(R1)1) (?(R2)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + +/(?<A> (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + +/(?<A> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + +/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + +/^(?(DEFINE) (?<A> a) (?<B> b) ) (?&A) (?&B) /x + abcd + +/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT)) + (?(DEFINE) + (?<NAME_PAT>[a-z]+) + (?<ADDRESS_PAT>\d+) + )/x + metcalfe 33 + +/^(?(DEFINE) abc | xyz ) /x + +/(?(DEFINE) abc) xyz/xI + +/(?(DEFINE) abc){3} xyz/x + +/(a|)*\d/ + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/<lf> + a\rb + a\nb\<cr> + a\x85b\<anycrlf> + ** Failers + a\nb + a\nb\<any> + a\rb\<cr> + a\rb\<any> + a\x85b\<any> + a\rb\<anycrlf> + +/^abc./mgx<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + +/abc.$/mgx<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9 + +/a/<cr><any> + +/a/<any><crlf> + +/^a\Rb/<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + ** Failers + a\n\rb + +/^a\R*b/<bsr_unicode> + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + +/^a\R+b/<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + ** Failers + ab + +/^a\R{1,3}b/<bsr_unicode> + a\nb + a\n\rb + a\n\r\x85b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/^a[\R]b/<bsr_unicode> + aRb + ** Failers + a\nb + +/(?&abc)X(?<abc>P)/I + abcPXP123 + +/(?1)X(?<abc>P)/I + abcPXP123 + +/(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ + 1.2.3.4 + 131.111.10.206 + 10.0.0.0 + ** Failers + 10.6 + 455.3.4.5 + +/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ + 1.2.3.4 + 131.111.10.206 + 10.0.0.0 + ** Failers + 10.6 + 455.3.4.5 + +/(?:a(?&abc)b)*(?<abc>x)/ + 123axbaxbaxbx456 + 123axbaxbaxb456 + +/(?:a(?&abc)b){1,5}(?<abc>x)/ + 123axbaxbaxbx456 + +/(?:a(?&abc)b){2,5}(?<abc>x)/ + 123axbaxbaxbx456 + +/(?:a(?&abc)b){2,}(?<abc>x)/ + 123axbaxbaxbx456 + +/(abc)(?i:(?1))/ + defabcabcxyz + DEFabcABCXYZ + +/(abc)(?:(?i)(?1))/ + defabcabcxyz + DEFabcABCXYZ + +/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ + ababababbbabZXXXX + +/^(a)\g-2/ + +/^(a)\g/ + +/^(a)\g{0}/ + +/^(a)\g{3/ + +/^(a)\g{4a}/ + +/^a.b/<lf> + a\rb + *** Failers + a\nb + +/.+foo/ + afoo + ** Failers + \r\nfoo + \nfoo + +/.+foo/<crlf> + afoo + \nfoo + ** Failers + \r\nfoo + +/.+foo/<any> + afoo + ** Failers + \nfoo + \r\nfoo + +/.+foo/s + afoo + \r\nfoo + \nfoo + +/^$/mg<any> + abc\r\rxyz + abc\n\rxyz + ** Failers + abc\r\nxyz + +/(?m)^$/<any>g+ + abc\r\n\r\n + +/(?m)^$|^\r\n/<any>g+ + abc\r\n\r\n + +/(?m)$/<any>g+ + abc\r\n\r\n + +/abc.$/mgx<anycrlf> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + +/^X/m + XABC + ** Failers + XABC\B + +/(ab|c)(?-1)/BZ + abc + +/xy(?+1)(abc)/BZ + xyabcabc + ** Failers + xyabc + +/x(?-0)y/ + +/x(?-1)y/ + +/x(?+0)y/ + +/x(?+1)y/ + +/^(abc)?(?(-1)X|Y)/BZ + abcX + Y + ** Failers + abcY + +/^((?(+1)X|Y)(abc))+/BZ + YabcXabc + YabcXabcXabc + ** Failers + XabcXabc + +/(?(-1)a)/BZ + +/((?(-1)a))/BZ + +/((?(-2)a))/BZ + +/^(?(+1)X|Y)(.)/BZ + Y! + +/(foo)\Kbar/ + foobar + +/(foo)(\Kbar|baz)/ + foobar + foobaz + +/(foo\Kbar)baz/ + foobarbaz + +/(?<A>tom|bon)-\k{A}/ + tom-tom + bon-bon + ** Failers + tom-bon + +/(?<A>tom|bon)-\g{A}/ + tom-tom + bon-bon + +/\g{A/ + +/(?|(abc)|(xyz))/BZ + >abc< + >xyz< + +/(x)(?|(abc)|(xyz))(x)/BZ + xabcx + xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/BZ + xabcpqrx + xxyzx + +/(?|(abc)|(xyz))\1/ + abcabc + xyzxyz + ** Failers + abcxyz + xyzabc + +/(?|(abc)|(xyz))(?1)/ + abcabc + xyzabc + ** Failers + xyzxyz + +/\H\h\V\v/ + X X\x0a + X\x09X\x0b + ** Failers + \xa0 X\x0a + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c + ** Failers + \x09\x20\xa0\x0a\x0b + +/\H{3,4}/ + XY ABCDE + XY PQR ST + +/.\h{3,4}./ + XY AB PQRS + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + > X NYQZ + ** Failers + >XYZ + > X NY Z + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/[\h]/BZ + >\x09< + +/[\h]+/BZ + >\x09\x20\xa0< + +/[\v]/BZ + +/[\H]/BZ + +/[^\h]/BZ + +/[\V]/BZ + +/[\x0a\V]/BZ + +/\H++X/BZ + ** Failers + XXXX + +/\H+\hY/BZ + XXXX Y + +/\H+ Y/BZ + +/\h+A/BZ + +/\v*B/BZ + +/\V+\x0a/BZ + +/A+\h/BZ + +/ *\H/BZ + +/A*\v/BZ + +/\x0b*\V/BZ + +/\d+\h/BZ + +/\d*\v/BZ + +/S+\h\S+\v/BZ + +/\w{3,}\h\w+\v/BZ + +/\h+\d\h+\w\h+\S\h+\H/BZ + +/\v+\d\v+\w\v+\S\v+\V/BZ + +/\H+\h\H+\d/BZ + +/\V+\v\V+\w/BZ + +/\( (?: [^()]* | (?R) )* \)/x +(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + +/[\E]AAA/ + +/[\Q\E]AAA/ + +/[^\E]AAA/ + +/[^\Q\E]AAA/ + +/[\E^]AAA/ + +/[\Q\E^]AAA/ + +/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ + +/^a+(*FAIL)/ + aaaaaa + +/a+b?c+(*FAIL)/ + aaabccc + +/a+b?(*PRUNE)c+(*FAIL)/ + aaabccc + +/a+b?(*COMMIT)c+(*FAIL)/ + aaabccc + +/a+b?(*SKIP)c+(*FAIL)/ + aaabcccaaabccc + +/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + aaa++++++ + bbbxxxxx + bbb+++++ + cccxxxx + ccc++++ + dddddddd + +/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + aaa++++++ + bbbxxxxx + bbb+++++ + cccxxxx + ccc++++ + dddddddd + +/a+b?(*THEN)c+(*FAIL)/ + aaabccc + +/(A (A|B(*ACCEPT)|C) D)(E)/x + ABX + AADE + ACDE + ** Failers + AD + +/^a+(*FAIL)/C + aaaaaa + +/a+b?c+(*FAIL)/C + aaabccc + +/a+b?(*PRUNE)c+(*FAIL)/C + aaabccc + +/a+b?(*COMMIT)c+(*FAIL)/C + aaabccc + +/a+b?(*SKIP)c+(*FAIL)/C + aaabcccaaabccc + +/a+b?(*THEN)c+(*FAIL)/C + aaabccc + +/a(*PRUNE:XXX)b/ + +/a(*MARK)b/ + +/(?i:A{1,}\6666666666)/ + +/\g6666666666/ + +/[\g6666666666]/ + +/(?1)\c[/ + +/.+A/<crlf> + \r\nA + +/\nA/<crlf> + \r\nA + +/[\r\n]A/<crlf> + \r\nA + +/(\r|\n)A/<crlf> + \r\nA + +/a(*CR)b/ + +/(*CR)a.b/ + a\nb + ** Failers + a\rb + +/(*CR)a.b/<lf> + a\nb + ** Failers + a\rb + +/(*LF)a.b/<CRLF> + a\rb + ** Failers + a\nb + +/(*CRLF)a.b/ + a\rb + a\nb + ** Failers + a\r\nb + +/(*ANYCRLF)a.b/<CR> + ** Failers + a\rb + a\nb + a\r\nb + +/(*ANY)a.b/<cr> + ** Failers + a\rb + a\nb + a\r\nb + a\x85b + +/a\Rb/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R{2,4}b/I<bsr_anycrlf> + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I<bsr_unicode> + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\<bsr_anycrlf> + a\x0b\0bb\<bsr_anycrlf> + +/(*BSR_ANYCRLF)a\Rb/I + a\nb + a\rb + +/(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I + a\nb + a\rb + +/(*CRLF)(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I + +/(?<a>)(?&)/ + +/(?<abc>)(?&a)/ + +/(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ + +/(?+-a)/ + +/(?-+a)/ + +/(?(-1))/ + +/(?(+10))/ + +/(?(10))/ + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ + +/\k<>/ + +/\k{}/ + +/(?P=)/ + +/(?P>)/ + +/(?!\w)(?R)/ + +/(?=\w)(?R)/ + +/(?<!\w)(?R)/ + +/(?<=\w)(?R)/ + +/[[:foo:]]/ + +/[[:1234:]]/ + +/[[:f\oo:]]/ + +/[[: :]]/ + +/[[:...:]]/ + +/[[:l\ower:]]/ + +/[[:abc\:]]/ + +/[abc[:x\]pqr:]]/ + +/[[:a\dz:]]/ + +/^(?<name>a|b\g<name>c)/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/^(?<name>a|b\g'name'c)/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/^(a|b\g<1>c)/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/^(a|b\g'1'c)/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/^(a|b\g'-1'c)/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/(^(a|b\g<-1>c))/ + aaaa + bacxxx + bbaccxxx + bbbacccxx + +/(^(a|b\g<-1'c))/ + +/(^(a|b\g{-1}))/ + bacxxx + +/(?-i:\g<name>)(?i:(?<name>a))/ + XaaX + XAAX + +/(?i:\g<name>)(?-i:(?<name>a))/ + XaaX + ** Failers + XAAX + +/(?-i:\g<+1>)(?i:(a))/ + XaaX + XAAX + +/(?=(?<regex>(?#simplesyntax)\$(?<name>[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?<index>[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g<name>)\]|->\g<name>(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g<name>(?<indices>\[(?:\g<index>|'(?:\\.|[^'\\])*'|"(?:\g<regex>|\\.|[^"\\])*")\])?|\g<complex>|\$\{\g<complex>\})\}|(?#complexsyntax)\{(?<complex>\$(?<segment>\g<name>(\g<indices>*|\(.*?\))?)(?:->\g<segment>)*|\$\g<complex>|\$\{\g<complex>\})\}))\{/ + +/(?<n>a|b|c)\g<n>*/ + abc + accccbbb + +/^(?+1)(?<a>x|y){0}z/ + xzxx + yzyy + ** Failers + xxz + +/(\3)(\1)(a)/ + cat + +/(\3)(\1)(a)/<JS> + cat + +/TA]/ + The ACTA] comes + +/TA]/<JS> + The ACTA] comes + +/(?2)[]a()b](abc)/ + abcbabc + +/(?2)[^]a()b](abc)/ + abcbabc + +/(?1)[]a()b](abc)/ + abcbabc + ** Failers + abcXabc + +/(?1)[^]a()b](abc)/ + abcXabc + ** Failers + abcbabc + +/(?2)[]a()b](abc)(xyz)/ + xyzbabcxyz + +/(?&N)[]a(?<N>)](?<M>abc)/ + abc<abc + +/(?&N)[]a(?<N>)](abc)/ + abc<abc + +/a[]b/ + +/a[^]b/ + +/a[]b/<JS> + ** Failers + ab + +/a[]+b/<JS> + ** Failers + ab + +/a[]*+b/<JS> + ** Failers + ab + +/a[^]b/<JS> + aXb + a\nb + ** Failers + ab + +/a[^]+b/<JS> + aXb + a\nX\nXb + ** Failers + ab + +/a(?!)+b/ + +/a(*FAIL)+b/ + +/(abc|pqr|123){0}[xyz]/SI + +/(?(?=.*b)b|^)/CI + adc + abc + +/(?(?=b).*b|^d)/I + +/(?(?=.*b).*b|^d)/I + +/a?|b?/P + abc + ** Failers + ddd\N + +/xyz/C + xyz + abcxyz + abcxyz\Y + ** Failers + abc + abc\Y + abcxypqr + abcxypqr\Y + +/^"((?(?=[a])[^"])|b)*"$/C + "ab" + +/^"((?(?=[a])[^"])|b)*"$/ + "ab" + +/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/ + XYabcdY + +/^X(?5)(a)(?|(b)|(q))(c)(d)Y/ + XYabcdY + +/^X(?&N)(a)(?|(b)|(q))(c)(d)(?<N>Y)/ + XYabcdY + +/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/ + XYabcdY + +/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/ + XYabcdY + +/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/ + XYabcdY / End of testinput2 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput3 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput3 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput3 Mon Jun 8 18:51:30 2009 @@ -86,6 +86,6 @@ >>>\xaa<<< >>>\xba<<< -/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR / End of testinput3 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput4 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput4 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput4 Mon Jun 8 18:51:30 2009 @@ -520,4 +520,107 @@ abcdefg ab +/a*\x{100}*\w/8 + a + +/\S\S/8g + A\x{a3}BC + +/\S{2}/8g + A\x{a3}BC + +/\W\W/8g + +\x{a3}== + +/\W{2}/8g + +\x{a3}== + +/\S/8g + \x{442}\x{435}\x{441}\x{442} + +/[\S]/8g + \x{442}\x{435}\x{441}\x{442} + +/\D/8g + \x{442}\x{435}\x{441}\x{442} + +/[\D]/8g + \x{442}\x{435}\x{441}\x{442} + +/\W/8g + \x{2442}\x{2435}\x{2441}\x{2442} + +/[\W]/8g + \x{2442}\x{2435}\x{2441}\x{2442} + +/[\S\s]*/8 + abc\n\r\x{442}\x{435}\x{441}\x{442}xyz + +/[\x{41f}\S]/8g + \x{442}\x{435}\x{441}\x{442} + +/.[^\S]./8g + abc def\x{442}\x{443}xyz\npqr + +/.[^\S\n]./8g + abc def\x{442}\x{443}xyz\npqr + +/[[:^alnum:]]/8g + +\x{2442} + +/[[:^alpha:]]/8g + +\x{2442} + +/[[:^ascii:]]/8g + A\x{442} + +/[[:^blank:]]/8g + A\x{442} + +/[[:^cntrl:]]/8g + A\x{442} + +/[[:^digit:]]/8g + A\x{442} + +/[[:^graph:]]/8g + \x19\x{e01ff} + +/[[:^lower:]]/8g + A\x{422} + +/[[:^print:]]/8g + \x{19}\x{e01ff} + +/[[:^punct:]]/8g + A\x{442} + +/[[:^space:]]/8g + A\x{442} + +/[[:^upper:]]/8g + a\x{442} + +/[[:^word:]]/8g + +\x{2442} + +/[[:^xdigit:]]/8g + M\x{442} + +/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉƊƋƎƏƐƑƓƔƖƗƘƜƝƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀʁʂʃʄʅʆʇʈʉʊʋʌʍʎʏʐʑʒʓʔʕʖʗʘʙʚʛʜʝʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯΐάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώϐϑϕϖϗϙϛϝϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹԁԃԅԇԉԋԍԏաբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆևᴀᴁᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌᴍᴎᴏᴐᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜᴝᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀᶁᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌᶍᶎᶏᶐᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇῐῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣⳤⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥfffiflffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 + +/^[^d]*?$/ + abc + +/^[^d]*?$/8 + abc + +/^[^d]*?$/i + abc + +/^[^d]*?$/8i + abc + +/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8 + / End of testinput4 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput5 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput5 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput5 Mon Jun 8 18:51:30 2009 @@ -1,20 +1,20 @@ -/\x{100}/8DM +/\x{100}/8DZ -/\x{1000}/8DM +/\x{1000}/8DZ -/\x{10000}/8DM +/\x{10000}/8DZ -/\x{100000}/8DM +/\x{100000}/8DZ -/\x{1000000}/8DM +/\x{1000000}/8DZ -/\x{4000000}/8DM +/\x{4000000}/8DZ -/\x{7fffFFFF}/8DM +/\x{7fffFFFF}/8DZ -/[\x{ff}]/8DM +/[\x{ff}]/8DZ -/[\x{100}]/8DM +/[\x{100}]/8DZ /\x{ffffffff}/8 @@ -23,39 +23,39 @@ /^\x{100}a\x{1234}/8 \x{100}a\x{1234}bcd -/\x80/8D +/\x80/8DZ -/\xff/8D +/\xff/8DZ -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 +/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 \x{0041}\x{2262}\x{0391}\x{002e} -/\x{D55c}\x{ad6d}\x{C5B4}/D8 +/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 \x{D55c}\x{ad6d}\x{C5B4} -/\x{65e5}\x{672c}\x{8a9e}/D8 +/\x{65e5}\x{672c}\x{8a9e}/DZ8 \x{65e5}\x{672c}\x{8a9e} -/\x{80}/D8 +/\x{80}/DZ8 -/\x{084}/D8 +/\x{084}/DZ8 -/\x{104}/D8 +/\x{104}/DZ8 -/\x{861}/D8 +/\x{861}/DZ8 -/\x{212ab}/D8 +/\x{212ab}/DZ8 -/.{3,5}X/D8 +/.{3,5}X/DZ8 \x{212ab}\x{212ab}\x{212ab}\x{861}X -/.{3,5}?/D8 +/.{3,5}?/DZ8 \x{212ab}\x{212ab}\x{212ab}\x{861} -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ +/-- These tests are here rather than in testinput4 because Perl 5.6 has some +problems with UTF-8 support, in the area of \x{..} where the value is < 255. +It grumbles about invalid UTF-8 strings. --/ /^[a\x{c0}]b/8 \x{c0}b @@ -80,29 +80,29 @@ /(?<=\C)X/8 Should produce an error diagnostic -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -/-- character, and you can't tell the difference.) --/ +/-- This one is here not because it's different to Perl, but because the way +the captured single-byte is displayed. (In Perl it becomes a character, and you +can't tell the difference.) --/ /X(\C)(.*)/8 X\x{1234} X\nabc -/^[ab]/8D +/^[ab]/8DZ bar *** Failers c \x{ff} \x{100} -/^[^ab]/8D +/^[^ab]/8DZ c \x{ff} \x{100} *** Failers aaa -/[^ab\xC0-\xF0]/8SD +/[^ab\xC0-\xF0]/8SDZ \x{f1} \x{bf} \x{100} @@ -111,16 +111,16 @@ \x{c0} \x{f0} -/Ā{3,4}/8SD +/Ā{3,4}/8SDZ \x{100}\x{100}\x{100}\x{100\x{100} -/(\x{100}+|x)/8SD +/(\x{100}+|x)/8SDZ -/(\x{100}*a|x)/8SD +/(\x{100}*a|x)/8SDZ -/(\x{100}{0,2}a|x)/8SD +/(\x{100}{0,2}a|x)/8SDZ -/(\x{100}{1,2}a|x)/8SD +/(\x{100}{1,2}a|x)/8SDZ /\x{100}*(\d+|"(?1)")/8 1234 @@ -132,34 +132,34 @@ *** Failers \x{100}\x{100}abcd -/\x{100}/8D +/\x{100}/8DZ -/\x{100}*/8D +/\x{100}*/8DZ -/a\x{100}*/8D +/a\x{100}*/8DZ -/ab\x{100}*/8D +/ab\x{100}*/8DZ -/a\x{100}\x{101}*/8D +/a\x{100}\x{101}*/8DZ -/a\x{100}\x{101}+/8D +/a\x{100}\x{101}+/8DZ -/\x{100}*A/8D +/\x{100}*A/8DZ A -/\x{100}*\d(?R)/8D +/\x{100}*\d(?R)/8DZ -/[^\x{c4}]/D +/[^\x{c4}]/DZ -/[^\x{c4}]/8D +/[^\x{c4}]/8DZ -/[\x{100}]/8DM +/[\x{100}]/8DZ \x{100} Z\x{100} \x{100}Z *** Failers -/[Z\x{100}]/8DM +/[Z\x{100}]/8DZ Z\x{100} \x{100} \x{100}Z @@ -174,21 +174,21 @@ \x{105} \x{ff} -/[z-\x{100}]/8D +/[z-\x{100}]/8DZ -/[z\Qa-d]Ā\E]/8D +/[z\Qa-d]Ā\E]/8DZ \x{100} Ā -/[\xFF]/D +/[\xFF]/DZ >\xff< -/[\xff]/D8 +/[\xff]/DZ8 >\x{ff}< -/[^\xFF]/D +/[^\xFF]/DZ -/[^\xff]/8D +/[^\xff]/8DZ /[Ä-Ü]/8 Ö # Matches without Study @@ -212,7 +212,7 @@ /���xxx/8 -/���xxx/8?D +/���xxx/8?DZ /abc/8 �] @@ -238,20 +238,24 @@ \xf9\x87\x80\x80\x80 \xfc\x84\x80\x80\x80\x80 \xfd\x83\x80\x80\x80\x80 + \?\xf8\x88\x80\x80\x80 + \?\xf9\x87\x80\x80\x80 + \?\xfc\x84\x80\x80\x80\x80 + \?\xfd\x83\x80\x80\x80\x80 -/\x{100}abc(xyz(?1))/8D +/\x{100}abc(xyz(?1))/8DZ -/[^\x{100}]abc(xyz(?1))/8D +/[^\x{100}]abc(xyz(?1))/8DZ -/[ab\x{100}]abc(xyz(?1))/8D +/[ab\x{100}]abc(xyz(?1))/8DZ -/(\x{100}(b(?2)c))?/D8 +/(\x{100}(b(?2)c))?/DZ8 -/(\x{100}(b(?2)c)){0,2}/D8 +/(\x{100}(b(?2)c)){0,2}/DZ8 -/(\x{100}(b(?1)c))?/D8 +/(\x{100}(b(?1)c))?/DZ8 -/(\x{100}(b(?1)c)){0,2}/D8 +/(\x{100}(b(?1)c)){0,2}/DZ8 /\W/8 A.B @@ -263,12 +267,222 @@ /a\x{1234}b/P8 a\x{1234}b -/^\ሴ/8D +/^\ሴ/8DZ /\777/I /\777/8I \x{1ff} \777 + +/\x{100}*\d/8DZ + +/\x{100}*\s/8DZ + +/\x{100}*\w/8DZ + +/\x{100}*\D/8DZ + +/\x{100}*\S/8DZ + +/\x{100}*\W/8DZ + +/\x{100}+\x{200}/8DZ + +/\x{100}+X/8DZ + +/X+\x{200}/8DZ + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/8x + AxxB + +/^[\x{100}\E-\Q\E\x{150}]/BZ8 + +/^[\QĀ\E-\QŐ\E]/BZ8 + +/^[\QĀ\E-\QŐ\E/BZ8 + +/^abc./mgx8<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx8<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/8<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/8<bsr_unicode> + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/8<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/8<bsr_unicode> + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\H\h\V\v/8 + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/[\h]/8BZ + >\x{1680} + +/[\h]{3,}/8BZ + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + +/[\v]/8BZ + +/[\H]/8BZ + +/[\V]/8BZ + +/.*$/8<any> + \x{1ec5} + +/-- This tests the stricter UTF-8 check according to RFC 3629. --/ + +/X/8 + \x{0}\x{d7ff}\x{e000}\x{10ffff} + \x{d800} + \x{d800}\? + \x{da00} + \x{da00}\? + \x{dfff} + \x{dfff}\? + \x{110000} + \x{110000}\? + \x{2000000} + \x{2000000}\? + \x{7fffffff} + \x{7fffffff}\? + +/a\Rb/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/.*a.*=.b.*/8<ANY> + QQQ\x{2029}ABCaXYZ=!bPQR + ** Failers + a\x{2029}b + \x61\xe2\x80\xa9\x62 + +/[[:a\x{100}b:]]/8 + +/a[^]b/<JS>8 + a\x{1234}b + a\nb + ** Failers + ab + +/a[^]+b/<JS>8 + aXb + a\nX\nX\x{1234}b + ** Failers + ab + +/(\x{de})\1/ + \x{de}\x{de} + \x{123} + +/X/8f<any> + A\x{1ec5}ABCXYZ + +/(*UTF8)\x{1234}/ + abcd\x{1234}pqr + +/(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I / End of testinput5 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput6 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput6 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput6 Mon Jun 8 18:51:30 2009 @@ -61,7 +61,7 @@ \x{09f} /^\p{Cs}/8 - \x{dfff} + \?\x{dfff} ** Failers \x{09f} @@ -69,7 +69,7 @@ a ** Failers Z - \x{dfff} + \x{e000} /^\p{Lm}/8 \x{2b0} @@ -323,20 +323,20 @@ ** Failers WXYZ -/[\p{L}]/D +/[\p{L}]/DZ -/[\p{^L}]/D +/[\p{^L}]/DZ -/[\P{L}]/D +/[\P{L}]/DZ -/[\P{^L}]/D +/[\P{^L}]/DZ -/[abc\p{L}\x{0660}]/8D +/[abc\p{L}\x{0660}]/8DZ -/[\p{Nd}]/8DM +/[\p{Nd}]/8DZ 1234 -/[\p{Nd}+-]+/8DM +/[\p{Nd}+-]+/8DZ 1234 12-34 12+\x{661}-34 @@ -425,13 +425,13 @@ A\x{391}\x{10427}\x{ff5a}\x{1fb0} A\x{391}\x{10427}\x{ff3a}\x{1fb8} -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iDZ -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8DZ -/AB\x{1fb0}/8D +/AB\x{1fb0}/8DZ -/AB\x{1fb0}/8Di +/AB\x{1fb0}/8DZi /\x{391}+/8i \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391} @@ -452,7 +452,7 @@ \x{c0} \x{e0} -/[\x{105}-\x{109}]/8iD +/[\x{105}-\x{109}]/8iDZ \x{104} \x{105} \x{109} @@ -460,7 +460,7 @@ \x{100} \x{10a} -/[z-\x{100}]/8iD +/[z-\x{100}]/8iDZ Z z \x{39c} @@ -475,7 +475,7 @@ Y y -/[z-\x{100}]/8Di +/[z-\x{100}]/8DZi /^\X/8 A @@ -747,4 +747,208 @@ /([\pL]=(abc))*X/ L=abcX +/The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE +will match it only with UCP support, because without that it has no notion +of case for anything other than the ASCII letters. / + +/((?i)[\x{c0}])/8 + \x{c0} + \x{e0} + +/(?i:[\x{c0}])/8 + \x{c0} + \x{e0} + +/^\p{Balinese}\p{Cuneiform}\p{Nko}\p{Phags_Pa}\p{Phoenician}/8 + \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900} + +/The next two are special cases where the lengths of the different cases of the +same character differ. The first went wrong with heap frame storage; the 2nd +was broken in all cases./ + +/^\x{023a}+?(\x{0130}+)/8i + \x{023a}\x{2c65}\x{0130} + +/^\x{023a}+([^X])/8i + \x{023a}\x{2c65}X + +/Check property support in non-UTF-8 mode/ + +/\p{L}{4}/ + 123abcdefg + 123abc\xc4\xc5zz + +/\X{1,3}\d/ + \x8aBCD + +/\X?\d/ + \x8aBCD + +/\P{L}?\d/ + \x8aBCD + +/[\PPP\x8a]{1,}\x80/ + A\x80 + +/(?:[\PPa*]*){8,}/ + +/[\P{Any}]/BZ + +/[\P{Any}\E]/BZ + +/(\P{Yi}+\277)/ + +/(\P{Yi}+\277)?/ + +/(?<=\P{Yi}{3}A)X/ + +/\p{Yi}+(\P{Yi}+)(?1)/ + +/(\P{Yi}{2}\277)?/ + +/[\P{Yi}A]/ + +/[\P{Yi}\P{Yi}\P{Yi}A]/ + +/[^\P{Yi}A]/ + +/[^\P{Yi}\P{Yi}\P{Yi}A]/ + +/(\P{Yi}*\277)*/ + +/(\P{Yi}*?\277)*/ + +/(\p{Yi}*+\277)*/ + +/(\P{Yi}?\277)*/ + +/(\P{Yi}??\277)*/ + +/(\p{Yi}?+\277)*/ + +/(\P{Yi}{0,3}\277)*/ + +/(\P{Yi}{0,3}?\277)*/ + +/(\p{Yi}{0,3}+\277)*/ + +/^[\p{Arabic}]/8 + \x{60e} + \x{656} + \x{657} + \x{658} + \x{659} + \x{65a} + \x{65b} + \x{65c} + \x{65d} + \x{65e} + \x{66a} + \x{6e9} + \x{6ef} + \x{6fa} + ** Failers + \x{600} + \x{650} + \x{651} + \x{652} + \x{653} + \x{654} + \x{655} + \x{65f} + +/^\p{Cyrillic}/8 + \x{1d2b} + +/^\p{Common}/8 + \x{589} + \x{60c} + \x{61f} + \x{964} + \x{965} + \x{970} + +/^\p{Inherited}/8 + \x{64b} + \x{654} + \x{655} + \x{200c} + ** Failers + \x{64a} + \x{656} + +/^\p{Shavian}/8 + \x{10450} + \x{1047f} + +/^\p{Deseret}/8 + \x{10400} + \x{1044f} + +/^\p{Osmanya}/8 + \x{10480} + \x{1049d} + \x{104a0} + \x{104a9} + ** Failers + \x{1049e} + \x{1049f} + \x{104aa} + +/\p{Zl}{2,3}+/8BZ + \xe2\x80\xa8\xe2\x80\xa8 + \x{2028}\x{2028}\x{2028} + +/\p{Zl}/8BZ + +/\p{Lu}{3}+/8BZ + +/\pL{2}+/8BZ + +/\p{Cc}{2}+/8BZ + +/\x{c0}+\x{116}+/8i + \x{c0}\x{e0}\x{116}\x{117} + +/[\x{c0}\x{116}]+/8i + \x{c0}\x{e0}\x{116}\x{117} + +/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8 + \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}==== + +/\x{a77d}\x{1d79}/8i + \x{a77d}\x{1d79} + \x{1d79}\x{a77d} + +/\x{a77d}\x{1d79}/8 + \x{a77d}\x{1d79} + ** Failers + \x{1d79}\x{a77d} + +/(A)\1/8i + AA + Aa + aa + aA + +/(\x{de})\1/8i + \x{de}\x{de} + \x{de}\x{fe} + \x{fe}\x{fe} + \x{fe}\x{de} + +/(\x{10a})\1/8i + \x{10a}\x{10a} + \x{10a}\x{10b} + \x{10b}\x{10b} + \x{10b}\x{10a} + +/The next two tests are for property support in non-UTF-8 mode/ + +/(?:\p{Lu}|\x20)+/ + \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59 + +/[\p{Lu}\x20]+/ + \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59 + / End of testinput6 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput7 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput7 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput7 Mon Jun 8 18:51:30 2009 @@ -1775,7 +1775,7 @@ abc /^a b -  c/x +  c/x abc /ab{1,3}bc/ @@ -1888,7 +1888,7 @@ /{4,5a}bc/ {4,5a}bc -/^a.b/ +/^a.b/<lf> a\rb *** Failers a\nb @@ -1931,8 +1931,8 @@ /(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ abcdefghijk\12S -/ab\gdef/ - abgdef +/ab\idef/ + abidef /a{0}bc/ bc @@ -2733,8 +2733,6 @@ abc abq -/ab{1,}bc/ - /ab+bc/ abbbbc @@ -4066,7 +4064,7 @@ xyz\rabc\<crlf> xyz\rabc\<lf> -/abc$/m +/abc$/m<lf> xyzabc xyzabc\n xyzabc\npqr @@ -4098,7 +4096,7 @@ ** Failers xyz\rabcdef -/.*/ +/.*/<lf> abc\ndef abc\rdef abc\r\ndef @@ -4114,4 +4112,313 @@ abc\rdef abc\r\ndef +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + +/^(a()*)*/ + aaaa + +/^(?:a(?:(?:))*)*/ + aaaa + +/^(a()+)+/ + aaaa + +/^(?:a(?:(?:))+)+/ + aaaa + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/<lf> + a\rb + a\nb\<cr> + ** Failers + a\nb + a\nb\<any> + a\rb\<cr> + a\rb\<any> + +/^abc./mgx<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + +/abc.$/mgx<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + +/^a\Rb/<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + ** Failers + a\n\rb + +/^a\R*b/<bsr_unicode> + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + +/^a\R+b/<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + ** Failers + ab + +/^a\R{1,3}b/<bsr_unicode> + a\nb + a\n\rb + a\n\r\x85b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/^a[\R]b/<bsr_unicode> + aRb + ** Failers + a\nb + +/.+foo/ + afoo + ** Failers + \r\nfoo + \nfoo + +/.+foo/<crlf> + afoo + \nfoo + ** Failers + \r\nfoo + +/.+foo/<any> + afoo + ** Failers + \nfoo + \r\nfoo + +/.+foo/s + afoo + \r\nfoo + \nfoo + +/^$/mg<any> + abc\r\rxyz + abc\n\rxyz + ** Failers + abc\r\nxyz + +/^X/m + XABC + ** Failers + XABC\B + +/(?m)^$/<any>g+ + abc\r\n\r\n + +/(?m)^$|^\r\n/<any>g+ + abc\r\n\r\n + +/(?m)$/<any>g+ + abc\r\n\r\n + +/(?|(abc)|(xyz))/ + >abc< + >xyz< + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + xyzabc + ** Failers + xyzxyz + +/\H\h\V\v/ + X X\x0a + X\x09X\x0b + ** Failers + \xa0 X\x0a + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c + ** Failers + \x09\x20\xa0\x0a\x0b + +/\H{3,4}/ + XY ABCDE + XY PQR ST + +/.\h{3,4}./ + XY AB PQRS + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + > X NYQZ + ** Failers + >XYZ + > X NY Z + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/<crlf> + \r\nA + +/\nA/<crlf> + \r\nA + +/[\r\n]A/<crlf> + \r\nA + +/(\r|\n)A/<crlf> + \r\nA + +/a\Rb/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R{2,4}b/I<bsr_anycrlf> + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I<bsr_unicode> + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\<bsr_anycrlf> + a\x0b\0bb\<bsr_anycrlf> + +/a(?!)|\wbc/ + abc + +/a[]b/<JS> + ** Failers + ab + +/a[]+b/<JS> + ** Failers + ab + +/a[]*+b/<JS> + ** Failers + ab + +/a[^]b/<JS> + aXb + a\nb + ** Failers + ab + +/a[^]+b/<JS> + aXb + a\nX\nXb + ** Failers + ab + +/X$/E + X + ** Failers + X\n + +/X$/ + X + X\n + +/xyz/C + xyz + abcxyz + abcxyz\Y + ** Failers + abc + abc\Y + abcxypqr + abcxypqr\Y + +/(?C)ab/ + ab + \C-ab + +/ab/C + ab + \C-ab + +/^"((?(?=[a])[^"])|b)*"$/C + "ab" + \C-"ab" + / End of testinput7 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput8 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput8 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput8 Mon Jun 8 18:51:30 2009 @@ -537,4 +537,134 @@ /^\x{85}$/8i \x{85} +/^abc./mgx8<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx8<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/8<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/8<bsr_unicode> + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/8<bsr_unicode> + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/8<bsr_unicode> + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\V?\v{3,4}/8 + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\h+\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\H\h\V\v/8 + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/a\Rb/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/X/8f<any> + A\x{1ec5}ABCXYZ + / End of testinput 8 / Modified: freeswitch/trunk/libs/pcre/testdata/testinput9 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testinput9 (original) +++ freeswitch/trunk/libs/pcre/testdata/testinput9 Mon Jun 8 18:51:30 2009 @@ -148,7 +148,7 @@ \x{09f} /^\p{Cs}/8 - \x{dfff} + \?\x{dfff} ** Failers \x{09f} @@ -156,7 +156,7 @@ a ** Failers Z - \x{dfff} + \x{e000} /^\p{Lm}/8 \x{2b0} @@ -813,4 +813,34 @@ \x{1c5}XY AXY +/^\x{023a}+?(\x{0130}+)/8i + \x{023a}\x{2c65}\x{0130} + +/^\x{023a}+([^X])/8i + \x{023a}\x{2c65}X + +/\x{c0}+\x{116}+/8i + \x{c0}\x{e0}\x{116}\x{117} + +/[\x{c0}\x{116}]+/8i + \x{c0}\x{e0}\x{116}\x{117} + +/Check property support in non-UTF-8 mode/ + +/\p{L}{4}/ + 123abcdefg + 123abc\xc4\xc5zz + +/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8 + \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}==== + +/\x{a77d}\x{1d79}/8i + \x{a77d}\x{1d79} + \x{1d79}\x{a77d} + +/\x{a77d}\x{1d79}/8 + \x{a77d}\x{1d79} + ** Failers + \x{1d79}\x{a77d} + / End / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput1 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput1 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput1 Mon Jun 8 18:51:30 2009 @@ -1817,7 +1817,7 @@ No match /^a b -  c/x +  c/x abc 0: abc @@ -2093,14 +2093,6 @@ {4,5a}bc 0: {4,5a}bc -/^a.b/ - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - /abc$/ abc 0: abc @@ -2197,9 +2189,9 @@ 10: j 11: k -/ab\gdef/ - abgdef - 0: abgdef +/ab\idef/ + abidef + 0: abidef /a{0}bc/ bc @@ -5480,12 +5472,22 @@ 0: b /^(?:a?b?)*$/ + \ + 0: + a + 0: a + ab + 0: ab + aaa + 0: aaa *** Failers No match dbcb No match a-- No match + aa-- +No match /((?s)^a(.))((?m)^b$)/ a\nb\nc\n @@ -5549,12 +5551,6 @@ 0: b 1: b -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - 0: a - /(x)?(?(1)a|b)/ *** Failers No match @@ -6353,4 +6349,301 @@ [a,b,c] 0: [a,b,c] +/(?-x: )/x + A\x20B + 0: + +"(?x)(?-x: \s*#\s*)" + A # B + 0: # + ** Failers +No match + # +No match + +"(?x-is)(?:(?-ixs) \s*#\s*) include" + A #include + 0: #include + ** Failers +No match + A#include +No match + A #Include +No match + +/a*b*\w/ + aaabbbb + 0: aaabbbb + aaaa + 0: aaaa + a + 0: a + +/a*b?\w/ + aaabbbb + 0: aaabb + aaaa + 0: aaaa + a + 0: a + +/a*b{0,4}\w/ + aaabbbb + 0: aaabbbb + aaaa + 0: aaaa + a + 0: a + +/a*b{0,}\w/ + aaabbbb + 0: aaabbbb + aaaa + 0: aaaa + a + 0: a + +/a*\d*\w/ + 0a + 0: 0a + a + 0: a + +/a*b *\w/x + a + 0: a + +/a*b#comment + *\w/x + a + 0: a + +/a* b *\w/x + a + 0: a + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + 0: abc=xyz\ + +/(?=(\w+))\1:/ + abcd: + 0: abcd: + 1: abcd + +/^(?=(\w+))\1:/ + abcd: + 0: abcd: + 1: abcd + +/^\Eabc/ + abc + 0: abc + +/^[\Eabc]/ + a + 0: a + ** Failers +No match + E +No match + +/^[a-\Ec]/ + b + 0: b + ** Failers +No match + - +No match + E +No match + +/^[a\E\E-\Ec]/ + b + 0: b + ** Failers +No match + - +No match + E +No match + +/^[\E\Qa\E-\Qz\E]+/ + b + 0: b + ** Failers +No match + - +No match + +/^[a\Q]bc\E]/ + a + 0: a + ] + 0: ] + c + 0: c + +/^[a-\Q\E]/ + a + 0: a + - + 0: - + +/^(a()*)*/ + aaaa + 0: aaaa + 1: a + 2: + +/^(?:a(?:(?:))*)*/ + aaaa + 0: aaaa + +/^(a()+)+/ + aaaa + 0: aaaa + 1: a + 2: + +/^(?:a(?:(?:))+)+/ + aaaa + 0: aaaa + +/(a){0,3}(?(1)b|(c|))*D/ + abbD + 0: abbD + 1: a + ccccD + 0: ccccD + 1: <unset> + 2: + D + 0: D + 1: <unset> + 2: + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 1: + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/\Z/g + abc\n + 0: + 0: + +/^(?s)(?>.*)(?<!\n)/ + abc + 0: abc + abc\n +No match + +/^(?![^\n]*\n\z)/ + abc + 0: + abc\n +No match + +/\z(?<!\n)/ + abc + 0: + abc\n +No match + +/(.*(.)?)*/ + abcd + 0: abcd + 1: + +/( (A | (?(1)0|) )* )/x + abcd + 0: + 1: + 2: + +/( ( (?(1)0|) )* )/x + abcd + 0: + 1: + 2: + +/( (?(1)0|)* )/x + abcd + 0: + 1: + +/[[:abcd:xyz]]/ + a] + 0: a] + :] + 0: :] + +/[abc[:x\]pqr]/ + a + 0: a + [ + 0: [ + : + 0: : + ] + 0: ] + p + 0: p + +/.*[op][xyz]/ + fooabcfoo +No match + +/(?(?=.*b)b|^)/ + adc + 0: + abc + 0: b + +/(?(?=^.*b)b|^)/ + adc + 0: + abc +No match + +/(?(?=.*b)b|^)*/ + adc + 0: + abc + 0: + +/(?(?=.*b)b|^)+/ + adc + 0: + abc + 0: b + +/(?(?=b).*b|^d)/ + abc + 0: b + +/(?(?=.*b).*b|^d)/ + abc + 0: ab + +/^%((?(?=[a])[^%])|b)*%$/ + %ab% + 0: %ab% + 1: + / End of testinput1 / Added: freeswitch/trunk/libs/pcre/testdata/testoutput10 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/testoutput10 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,669 @@ +/-- These are a few representative patterns whose lengths and offsets are to be +shown when the link size is 2. This is just a doublecheck test to ensure the +sizes don't go horribly wrong when something is changed. The pattern contents +are all themselves checked in other tests. --/ + +/((?i)b)/BM +Memory allocation (code space): 21 +------------------------------------------------------------------ + 0 17 Bra + 3 9 CBra 1 + 8 01 Opt + 10 NC b + 12 9 Ket + 15 00 Opt + 17 17 Ket + 20 End +------------------------------------------------------------------ + +/(?s)(.*X|^B)/BM +Memory allocation (code space): 25 +------------------------------------------------------------------ + 0 21 Bra + 3 9 CBra 1 + 8 AllAny* + 10 X + 12 6 Alt + 15 ^ + 16 B + 18 15 Ket + 21 21 Ket + 24 End +------------------------------------------------------------------ + +/(?s:.*X|^B)/BM +Memory allocation (code space): 29 +------------------------------------------------------------------ + 0 25 Bra + 3 9 Bra + 6 04 Opt + 8 AllAny* + 10 X + 12 8 Alt + 15 04 Opt + 17 ^ + 18 B + 20 17 Ket + 23 00 Opt + 25 25 Ket + 28 End +------------------------------------------------------------------ + +/^[[:alnum:]]/BM +Memory allocation (code space): 41 +------------------------------------------------------------------ + 0 37 Bra + 3 ^ + 4 [0-9A-Za-z] + 37 37 Ket + 40 End +------------------------------------------------------------------ + +/#/IxMD +Memory allocation (code space): 7 +------------------------------------------------------------------ + 0 3 Bra + 3 3 Ket + 6 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +No first char +No need char + +/a#/IxMD +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +First char = 'a' +No need char + +/x?+/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 x?+ + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/x++/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 x++ + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/x{1,3}+/BM +Memory allocation (code space): 19 +------------------------------------------------------------------ + 0 15 Bra + 3 9 Once + 6 x + 8 x{0,2} + 12 9 Ket + 15 15 Ket + 18 End +------------------------------------------------------------------ + +/(x)*+/BM +Memory allocation (code space): 24 +------------------------------------------------------------------ + 0 20 Bra + 3 14 Once + 6 Brazero + 7 7 CBra 1 + 12 x + 14 7 KetRmax + 17 14 Ket + 20 20 Ket + 23 End +------------------------------------------------------------------ + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/BM +Memory allocation (code space): 120 +------------------------------------------------------------------ + 0 116 Bra + 3 ^ + 4 109 CBra 1 + 9 7 CBra 2 + 14 a+ + 16 7 Ket + 19 39 CBra 3 + 24 [ab]+? + 58 39 Ket + 61 39 CBra 4 + 66 [bc]+ +100 39 Ket +103 7 CBra 5 +108 \w* +110 7 Ket +113 109 Ket +116 116 Ket +119 End +------------------------------------------------------------------ + +|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM +Memory allocation (code space): 826 +------------------------------------------------------------------ + 0 822 Bra + 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X +821 \b +822 822 Ket +825 End +------------------------------------------------------------------ + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM +Memory allocation (code space): 816 +------------------------------------------------------------------ + 0 812 Bra + 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X +811 \b +812 812 Ket +815 End +------------------------------------------------------------------ + +/(a(?1)b)/BM +Memory allocation (code space): 28 +------------------------------------------------------------------ + 0 24 Bra + 3 18 CBra 1 + 8 a + 10 6 Once + 13 3 Recurse + 16 6 Ket + 19 b + 21 18 Ket + 24 24 Ket + 27 End +------------------------------------------------------------------ + +/(a(?1)+b)/BM +Memory allocation (code space): 28 +------------------------------------------------------------------ + 0 24 Bra + 3 18 CBra 1 + 8 a + 10 6 Once + 13 3 Recurse + 16 6 KetRmax + 19 b + 21 18 Ket + 24 24 Ket + 27 End +------------------------------------------------------------------ + +/a(?P<name1>b|c)d(?P<longername2>e)/BM +Memory allocation (code space): 42 +------------------------------------------------------------------ + 0 32 Bra + 3 a + 5 7 CBra 1 + 10 b + 12 5 Alt + 15 c + 17 12 Ket + 20 d + 22 7 CBra 2 + 27 e + 29 7 Ket + 32 32 Ket + 35 End +------------------------------------------------------------------ + +/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/BM +Memory allocation (code space): 54 +------------------------------------------------------------------ + 0 41 Bra + 3 25 Bra + 6 a + 8 17 CBra 1 + 13 c + 15 7 CBra 2 + 20 d + 22 7 Ket + 25 17 Ket + 28 25 Ket + 31 7 CBra 3 + 36 a + 38 7 Ket + 41 41 Ket + 44 End +------------------------------------------------------------------ + +/(?P<a>a)...(?P=a)bbb(?P>a)d/BM +Memory allocation (code space): 43 +------------------------------------------------------------------ + 0 36 Bra + 3 7 CBra 1 + 8 a + 10 7 Ket + 13 Any + 14 Any + 15 Any + 16 \1 + 19 bbb + 25 6 Once + 28 3 Recurse + 31 6 Ket + 34 d + 36 36 Ket + 39 End +------------------------------------------------------------------ + +/abc(?C255)de(?C)f/BM +Memory allocation (code space): 31 +------------------------------------------------------------------ + 0 27 Bra + 3 abc + 9 Callout 255 10 1 + 15 de + 19 Callout 0 16 1 + 25 f + 27 27 Ket + 30 End +------------------------------------------------------------------ + +/abcde/CBM +Memory allocation (code space): 53 +------------------------------------------------------------------ + 0 49 Bra + 3 Callout 255 0 1 + 9 a + 11 Callout 255 1 1 + 17 b + 19 Callout 255 2 1 + 25 c + 27 Callout 255 3 1 + 33 d + 35 Callout 255 4 1 + 41 e + 43 Callout 255 5 0 + 49 49 Ket + 52 End +------------------------------------------------------------------ + +/\x{100}/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{100} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\x{1000}/8BM +Memory allocation (code space): 11 +------------------------------------------------------------------ + 0 7 Bra + 3 \x{1000} + 7 7 Ket + 10 End +------------------------------------------------------------------ + +/\x{10000}/8BM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra + 3 \x{10000} + 8 8 Ket + 11 End +------------------------------------------------------------------ + +/\x{100000}/8BM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra + 3 \x{100000} + 8 8 Ket + 11 End +------------------------------------------------------------------ + +/\x{1000000}/8BM +Memory allocation (code space): 13 +------------------------------------------------------------------ + 0 9 Bra + 3 \x{1000000} + 9 9 Ket + 12 End +------------------------------------------------------------------ + +/\x{4000000}/8BM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra + 3 \x{4000000} + 10 10 Ket + 13 End +------------------------------------------------------------------ + +/\x{7fffFFFF}/8BM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra + 3 \x{7fffffff} + 10 10 Ket + 13 End +------------------------------------------------------------------ + +/[\x{ff}]/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/[\x{100}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/\x80/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{80} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\xff/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 A\x{2262}\x{391}. + 14 14 Ket + 17 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 'A' +Need char = '.' + +/\x{D55c}\x{ad6d}\x{C5B4}/D8M +Memory allocation (code space): 19 +------------------------------------------------------------------ + 0 15 Bra + 3 \x{d55c}\x{ad6d}\x{c5b4} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 237 +Need char = 180 + +/\x{65e5}\x{672c}\x{8a9e}/D8M +Memory allocation (code space): 19 +------------------------------------------------------------------ + 0 15 Bra + 3 \x{65e5}\x{672c}\x{8a9e} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 230 +Need char = 158 + +/[\x{100}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[Z\x{100}]/8BM +Memory allocation (code space): 47 +------------------------------------------------------------------ + 0 43 Bra + 3 [Z\x{100}] + 43 43 Ket + 46 End +------------------------------------------------------------------ + +/^[\x{100}\E-\Q\E\x{150}]/B8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 ^ + 4 [\x{100}-\x{150}] + 14 14 Ket + 17 End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E]/B8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 ^ + 4 [\x{100}-\x{150}] + 14 14 Ket + 17 End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E/B8M +Failed: missing terminating ] for character class at offset 15 + +/[\p{L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\p{^L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\P{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\P{L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\P{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\P{^L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[abc\p{L}\x{0660}]/8BM +Memory allocation (code space): 50 +------------------------------------------------------------------ + 0 46 Bra + 3 [a-c\p{L}\x{660}] + 46 46 Ket + 49 End +------------------------------------------------------------------ + +/[\p{Nd}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{Nd}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\p{Nd}+-]+/8BM +Memory allocation (code space): 48 +------------------------------------------------------------------ + 0 44 Bra + 3 [+\-\p{Nd}]+ + 44 44 Ket + 47 End +------------------------------------------------------------------ + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM +Memory allocation (code space): 25 +------------------------------------------------------------------ + 0 21 Bra + 3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} + 21 21 Ket + 24 End +------------------------------------------------------------------ + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM +Memory allocation (code space): 25 +------------------------------------------------------------------ + 0 21 Bra + 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} + 21 21 Ket + 24 End +------------------------------------------------------------------ + +/[\x{105}-\x{109}]/8iBM +Memory allocation (code space): 17 +------------------------------------------------------------------ + 0 13 Bra + 3 [\x{104}-\x{109}] + 13 13 Ket + 16 End +------------------------------------------------------------------ + +/( ( (?(1)0|) )* )/xBM +Memory allocation (code space): 38 +------------------------------------------------------------------ + 0 34 Bra + 3 28 CBra 1 + 8 Brazero + 9 19 SCBra 2 + 14 8 Cond + 17 1 Cond ref + 20 0 + 22 3 Alt + 25 11 Ket + 28 19 KetRmax + 31 28 Ket + 34 34 Ket + 37 End +------------------------------------------------------------------ + +/( (?(1)0|)* )/xBM +Memory allocation (code space): 30 +------------------------------------------------------------------ + 0 26 Bra + 3 20 CBra 1 + 8 Brazero + 9 8 SCond + 12 1 Cond ref + 15 0 + 17 3 Alt + 20 11 KetRmax + 23 20 Ket + 26 26 Ket + 29 End +------------------------------------------------------------------ + +/[a]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[a]/8BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[\xaa]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 \xaa + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[\xaa]/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{aa} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/[^a]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^a] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^a]/8BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^a] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^\xaa]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^\xaa] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^\xaa]/8BM +Memory allocation (code space): 40 +------------------------------------------------------------------ + 0 36 Bra + 3 [\x00-\xa9\xab-\xff] (neg) + 36 36 Ket + 39 End +------------------------------------------------------------------ + +/ End of testinput10 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput2 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput2 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput2 Mon Jun 8 18:51:30 2009 @@ -1,10 +1,10 @@ -/(a)b|/ +/(a)b|/I Capturing subpattern count = 1 No options No first char No need char -/abc/ +/abc/I Capturing subpattern count = 0 No options First char = 'a' @@ -22,7 +22,7 @@ ABC No match -/^abc/ +/^abc/I Capturing subpattern count = 0 Options: anchored No first char @@ -38,35 +38,35 @@ \Adefabc No match -/a+bc/ +/a+bc/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'c' -/a*bc/ +/a*bc/I Capturing subpattern count = 0 Partial matching not supported No options No first char Need char = 'c' -/a{3}bc/ +/a{3}bc/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'c' -/(abc|a+z)/ +/(abc|a+z)/I Capturing subpattern count = 1 Partial matching not supported No options First char = 'a' No need char -/^abc$/ +/^abc$/I Capturing subpattern count = 0 Options: anchored No first char @@ -78,10 +78,10 @@ def\nabc No match -/ab\gdef/X +/ab\idef/X Failed: unrecognized character follows \ at offset 3 -/(?X)ab\gdef/X +/(?X)ab\idef/X Failed: unrecognized character follows \ at offset 7 /x{5,4}/ @@ -109,23 +109,23 @@ Failed: missing ) after comment at offset 7 /(?z)abc/ -Failed: unrecognized character after (? at offset 2 +Failed: unrecognized character after (? or (?- at offset 2 -/.*b/ +/.*b/I Capturing subpattern count = 0 Partial matching not supported No options First char at start or follows newline Need char = 'b' -/.*?b/ +/.*?b/I Capturing subpattern count = 0 Partial matching not supported No options First char at start or follows newline Need char = 'b' -/cat|dog|elephant/ +/cat|dog|elephant/I Capturing subpattern count = 0 No options No first char @@ -135,7 +135,7 @@ this sentences rambles on and on for a while and then reaches elephant 0: elephant -/cat|dog|elephant/S +/cat|dog|elephant/IS Capturing subpattern count = 0 No options No first char @@ -146,7 +146,7 @@ this sentences rambles on and on for a while and then reaches elephant 0: elephant -/cat|dog|elephant/iS +/cat|dog|elephant/IiS Capturing subpattern count = 0 Options: caseless No first char @@ -157,14 +157,14 @@ this sentences rambles on and on for a while to elephant ElePhant 0: elephant -/a|[bcd]/S +/a|[bcd]/IS Capturing subpattern count = 0 No options No first char No need char Starting byte set: a b c d -/(a|[^\dZ])/S +/(a|[^\dZ])/IS Capturing subpattern count = 1 No options No first char @@ -184,7 +184,7 @@ \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff -/(a|b)*[\s]/S +/(a|b)*[\s]/IS Capturing subpattern count = 1 No options No first char @@ -197,7 +197,7 @@ /{4,5}abc/ Failed: nothing to repeat at offset 4 -/(a)(b)(c)\2/ +/(a)(b)(c)\2/I Capturing subpattern count = 3 Max back reference = 2 No options @@ -222,13 +222,13 @@ 0: abcb 1: a 2: b - \O12abcb + \O12abcb 0: abcb 1: a 2: b 3: c -/(a)bc|(a)(b)\2/ +/(a)bc|(a)(b)\2/I Capturing subpattern count = 3 Max back reference = 2 No options @@ -270,7 +270,7 @@ 2: a 3: b -/abc$/E +/abc$/IE Capturing subpattern count = 0 Options: dollar_endonly First char = 'a' @@ -287,7 +287,7 @@ /(a)(b)(c)(d)(e)\6/ Failed: reference to non-existent subpattern at offset 17 -/the quick brown fox/ +/the quick brown fox/I Capturing subpattern count = 0 No options First char = 't' @@ -297,7 +297,7 @@ this is a line with the quick brown fox 0: the quick brown fox -/the quick brown fox/A +/the quick brown fox/IA Capturing subpattern count = 0 Options: anchored No first char @@ -310,9 +310,9 @@ No match /ab(?z)cd/ -Failed: unrecognized character after (? at offset 4 +Failed: unrecognized character after (? or (?- at offset 4 -/^abc|def/ +/^abc|def/I Capturing subpattern count = 0 No options No first char @@ -322,7 +322,7 @@ abcdef\B 0: def -/.*((abc)$|(def))/ +/.*((abc)$|(def))/I Capturing subpattern count = 3 Partial matching not supported No options @@ -338,19 +338,19 @@ 2: <unset> 3: def -/abc/P +/abc/IP abc 0: abc *** Failers No match: POSIX code 17: match failed - -/^abc|def/P + +/^abc|def/IP abcdef 0: abc abcdef\B 0: def -/.*((abc)$|(def))/P +/.*((abc)$|(def))/IP defabc 0: defabc 1: abc @@ -359,37 +359,37 @@ 0: def 1: def 3: def - -/the quick brown fox/P + +/the quick brown fox/IP the quick brown fox 0: the quick brown fox - *** Failers + *** Failers No match: POSIX code 17: match failed - The Quick Brown Fox + The Quick Brown Fox No match: POSIX code 17: match failed -/the quick brown fox/Pi +/the quick brown fox/IPi the quick brown fox 0: the quick brown fox - The Quick Brown Fox + The Quick Brown Fox 0: The Quick Brown Fox -/abc.def/P +/abc.def/IP *** Failers No match: POSIX code 17: match failed abc\ndef No match: POSIX code 17: match failed - -/abc$/P + +/abc$/IP abc 0: abc - abc\n + abc\n 0: abc -/(abc)\2/P +/(abc)\2/IP Failed: POSIX code 15: bad back reference at offset 7 -/(abc\1)/P +/(abc\1)/IP abc No match: POSIX code 17: match failed @@ -399,16 +399,16 @@ /a[]b/ Failed: missing terminating ] for character class at offset 4 -/[^aeiou ]{3,}/ +/[^aeiou ]{3,}/I Capturing subpattern count = 0 Partial matching not supported No options No first char No need char - co-processors, and for + co-processors, and for 0: -pr - -/<.*>/ + +/<.*>/I Capturing subpattern count = 0 Partial matching not supported No options @@ -417,7 +417,7 @@ abc<def>ghi<klm>nop 0: <def>ghi<klm> -/<.*?>/ +/<.*?>/I Capturing subpattern count = 0 Partial matching not supported No options @@ -426,7 +426,7 @@ abc<def>ghi<klm>nop 0: <def> -/<.*>/U +/<.*>/IU Capturing subpattern count = 0 Partial matching not supported Options: ungreedy @@ -434,8 +434,8 @@ Need char = '>' abc<def>ghi<klm>nop 0: <def> - -/(?U)<.*>/ + +/(?U)<.*>/I Capturing subpattern count = 0 Partial matching not supported Options: ungreedy @@ -444,7 +444,7 @@ abc<def>ghi<klm>nop 0: <def> -/<.*?>/U +/<.*?>/IU Capturing subpattern count = 0 Partial matching not supported Options: ungreedy @@ -452,8 +452,8 @@ Need char = '>' abc<def>ghi<klm>nop 0: <def>ghi<klm> - -/={3,}/U + +/={3,}/IU Capturing subpattern count = 0 Partial matching not supported Options: ungreedy @@ -461,8 +461,8 @@ Need char = '=' abc========def 0: === - -/(?U)={3,}?/ + +/(?U)={3,}?/I Capturing subpattern count = 0 Partial matching not supported Options: ungreedy @@ -470,21 +470,21 @@ Need char = '=' abc========def 0: ======== - -/(?<!bar|cattle)foo/ + +/(?<!bar|cattle)foo/I Capturing subpattern count = 0 No options First char = 'f' Need char = 'o' foo 0: foo - catfoo + catfoo 0: foo *** Failers No match the barfoo No match - and cattlefoo + and cattlefoo No match /(?<=a+)b/ @@ -496,65 +496,65 @@ /(?<!(foo)a\1)bar/ Failed: lookbehind assertion is not fixed length at offset 12 -/(?i)abc/ +/(?i)abc/I Capturing subpattern count = 0 Options: caseless First char = 'a' (caseless) Need char = 'c' (caseless) -/(a|(?m)a)/ +/(a|(?m)a)/I Capturing subpattern count = 1 No options First char = 'a' No need char -/(?i)^1234/ +/(?i)^1234/I Capturing subpattern count = 0 Options: anchored caseless No first char No need char -/(^b|(?i)^d)/ +/(^b|(?i)^d)/I Capturing subpattern count = 1 Options: anchored No first char No need char -/(?s).*/ +/(?s).*/I Capturing subpattern count = 0 Partial matching not supported Options: anchored dotall No first char No need char -/[abcd]/S +/[abcd]/IS Capturing subpattern count = 0 No options No first char No need char Starting byte set: a b c d -/(?i)[abcd]/S +/(?i)[abcd]/IS Capturing subpattern count = 0 Options: caseless No first char No need char Starting byte set: A B C D a b c d -/(?m)[xy]|(b|c)/S +/(?m)[xy]|(b|c)/IS Capturing subpattern count = 1 Options: multiline No first char No need char Starting byte set: b c x y -/(^a|^b)/m +/(^a|^b)/Im Capturing subpattern count = 1 Options: multiline First char at start or follows newline No need char -/(?i)(^a|^b)/m +/(?i)(^a|^b)/Im Capturing subpattern count = 1 Options: caseless multiline First char at start or follows newline @@ -567,6 +567,9 @@ Failed: conditional group contains more than two branches at offset 12 /(?(1a)/ +Failed: missing ) at offset 6 + +/(?(1a))/ Failed: reference to non-existent subpattern at offset 6 /(?(?i))/ @@ -576,9 +579,9 @@ Failed: reference to non-existent subpattern at offset 7 /(?(?<ab))/ -Failed: unrecognized character after (?< at offset 5 +Failed: syntax error in subpattern name (missing terminator) at offset 7 -/((?s)blah)\s+\1/ +/((?s)blah)\s+\1/I Capturing subpattern count = 1 Max back reference = 1 Partial matching not supported @@ -586,7 +589,7 @@ First char = 'b' Need char = 'h' -/((?i)blah)\s+\1/ +/((?i)blah)\s+\1/I Capturing subpattern count = 1 Max back reference = 1 Partial matching not supported @@ -594,16 +597,16 @@ First char = 'b' (caseless) Need char = 'h' (caseless) -/((?i)b)/DS +/((?i)b)/IDZS ------------------------------------------------------------------ - 0 15 Bra 0 - 3 7 Bra 1 - 6 01 Opt - 8 NC b - 10 7 Ket - 13 00 Opt - 15 15 Ket - 18 End + Bra + CBra 1 + 01 Opt + NC b + Ket + 00 Opt + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options @@ -611,7 +614,7 @@ No need char Study returned NULL -/(a*b|(?i:c*(?-i)d))/S +/(a*b|(?i:c*(?-i)d))/IS Capturing subpattern count = 1 Partial matching not supported No options @@ -619,7 +622,7 @@ No need char Starting byte set: C a b c d -/a$/ +/a$/I Capturing subpattern count = 0 No options First char = 'a' @@ -628,14 +631,14 @@ 0: a a\n 0: a - *** Failers + *** Failers No match \Za No match - \Za\n + \Za\n No match -/a$/m +/a$/Im Capturing subpattern count = 0 Options: multiline First char = 'a' @@ -644,26 +647,26 @@ 0: a a\n 0: a - \Za\n + \Za\n 0: a - *** Failers + *** Failers No match \Za No match - -/\Aabc/m + +/\Aabc/Im Capturing subpattern count = 0 Options: anchored multiline No first char No need char -/^abc/m +/^abc/Im Capturing subpattern count = 0 Options: multiline First char at start or follows newline Need char = 'c' -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I Capturing subpattern count = 5 Partial matching not supported Options: anchored @@ -677,60 +680,62 @@ 4: bbbbccccc 5: def -/(?<=foo)[ab]/S +/(?<=foo)[ab]/IS Capturing subpattern count = 0 No options No first char No need char Starting byte set: a b -/(?<!foo)(alpha|omega)/S +/(?<!foo)(alpha|omega)/IS Capturing subpattern count = 1 No options No first char Need char = 'a' Starting byte set: a o -/(?!alphabet)[ab]/S +/(?!alphabet)[ab]/IS Capturing subpattern count = 0 No options No first char No need char Starting byte set: a b -/(?<=foo\n)^bar/m +/(?<=foo\n)^bar/Im Capturing subpattern count = 0 +Contains explicit CR or LF match Options: multiline No first char Need char = 'r' - foo\nbarbar + foo\nbarbar 0: bar ***Failers No match - rhubarb + rhubarb No match barbell No match - abc\nbarton + abc\nbarton No match -/^(?<=foo\n)bar/m +/^(?<=foo\n)bar/Im Capturing subpattern count = 0 +Contains explicit CR or LF match Options: multiline First char at start or follows newline Need char = 'r' - foo\nbarbar + foo\nbarbar 0: bar ***Failers No match - rhubarb + rhubarb No match barbell No match - abc\nbarton + abc\nbarton No match -/(?>^abc)/m +/(?>^abc)/Im Capturing subpattern count = 0 Options: multiline First char at start or follows newline @@ -741,7 +746,7 @@ 0: abc *** Failers No match - defabc + defabc No match /(?<=ab(c+)d)ef/ @@ -754,12 +759,8 @@ Failed: lookbehind assertion is not fixed length at offset 13 /The next three are in testinput2 because they have variable length branches/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 's' -/(?<=bullock|donkey)-cart/ +/(?<=bullock|donkey)-cart/I Capturing subpattern count = 0 No options First char = '-' @@ -772,16 +773,16 @@ No match cart No match - horse-and-cart + horse-and-cart No match - -/(?<=ab(?i)x|y|z)/ + +/(?<=ab(?i)x|y|z)/I Capturing subpattern count = 0 No options No first char No need char -/(?>.*)(?<=(abcd)|(xyz))/ +/(?>.*)(?<=(abcd)|(xyz))/I Capturing subpattern count = 2 Partial matching not supported No options @@ -795,7 +796,7 @@ 1: <unset> 2: xyz -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I Capturing subpattern count = 0 No options First char = 'Z' @@ -810,56 +811,56 @@ 0: ZZ bZZ 0: ZZ - BZZ + BZZ 0: ZZ *** Failers No match - ZZ + ZZ No match - abXYZZ + abXYZZ No match zzz No match - bzz + bzz No match -/(?<!(foo)a)bar/ +/(?<!(foo)a)bar/I Capturing subpattern count = 1 No options First char = 'b' Need char = 'r' bar 0: bar - foobbar + foobbar 0: bar *** Failers No match - fooabar + fooabar No match -/This one is here because Perl 5.005_02 doesn't fail it/ +/This one is here because Perl 5.005_02 doesn't fail it/I Capturing subpattern count = 0 No options First char = 'T' Need char = 't' -/^(a)?(?(1)a|b)+$/ +/^(a)?(?(1)a|b)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char *** Failers No match - a + a No match -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ +/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/I Capturing subpattern count = 0 No options First char = 'T' Need char = 'g' -/^(a\1?){4}$/ +/^(a\1?){4}$/I Capturing subpattern count = 1 Max back reference = 1 Options: anchored @@ -868,8 +869,8 @@ aaaaaa 0: aaaaaa 1: aa - -/These are syntax tests from Perl 5.005/ + +/These are syntax tests from Perl 5.005/I Capturing subpattern count = 0 No options First char = 'T' @@ -911,31 +912,31 @@ /(a)|\2/ Failed: reference to non-existent subpattern at offset 6 -/a[b-a]/i +/a[b-a]/Ii Failed: range out of order in character class at offset 4 -/a[]b/i +/a[]b/Ii Failed: missing terminating ] for character class at offset 4 -/a[/i +/a[/Ii Failed: missing terminating ] for character class at offset 2 -/*a/i +/*a/Ii Failed: nothing to repeat at offset 0 -/(*)b/i +/(*)b/Ii Failed: nothing to repeat at offset 1 -/abc)/i +/abc)/Ii Failed: unmatched parentheses at offset 3 -/(abc/i +/(abc/Ii Failed: missing ) at offset 4 -/a**/i +/a**/Ii Failed: nothing to repeat at offset 2 -/)(/i +/)(/Ii Failed: unmatched parentheses at offset 0 /:(?:/ @@ -945,26 +946,23 @@ Failed: unrecognized character after (?< at offset 3 /a(?{)b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{{})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{}})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{"{"})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{"{"}})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /(?(1?)a|b)/ Failed: malformed number or name after (?( at offset 4 -/(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 10 - /[a[:xyz:/ Failed: missing terminating ] for character class at offset 8 @@ -983,7 +981,7 @@ /abc/\i Failed: \ at end of pattern at offset 4 -/(a)bc(d)/ +/(a)bc(d)/I Capturing subpattern count = 2 No options First char = 'a' @@ -1002,8 +1000,8 @@ 1: a 2: d copy substring 5 failed -7 - -/(.{20})/ + +/(.{20})/I Capturing subpattern count = 1 Partial matching not supported No options @@ -1020,8 +1018,8 @@ 0: abcdefghijklmnopqrst 1: abcdefghijklmnopqrst 1G abcdefghijklmnopqrst (20) - -/(.{15})/ + +/(.{15})/I Capturing subpattern count = 1 Partial matching not supported No options @@ -1036,7 +1034,7 @@ 1C abcdefghijklmno (15) 1G abcdefghijklmno (15) -/(.{16})/ +/(.{16})/I Capturing subpattern count = 1 Partial matching not supported No options @@ -1052,13 +1050,13 @@ 1G abcdefghijklmnop (16) 0L abcdefghijklmnop 1L abcdefghijklmnop - -/^(a|(bc))de(f)/ + +/^(a|(bc))de(f)/I Capturing subpattern count = 3 Options: anchored No first char No need char - adef\G1\G2\G3\G4\L + adef\G1\G2\G3\G4\L 0: adef 1: a 2: <unset> @@ -1071,7 +1069,7 @@ 1L a 2L 3L f - bcdef\G1\G2\G3\G4\L + bcdef\G1\G2\G3\G4\L 0: bcdef 1: bc 2: bc @@ -1084,40 +1082,40 @@ 1L bc 2L bc 3L f - adefghijk\C0 + adefghijk\C0 0: adef 1: a 2: <unset> 3: f 0C adef (4) - -/^abc\00def/ + +/^abc\00def/I Capturing subpattern count = 0 Options: anchored No first char No need char - abc\00def\L\C0 + abc\00def\L\C0 0: abc\x00def 0C abc (7) 0L abc - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/M -Memory allocation (code space): 432 + +/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)?)?)?)?)?)?)?)?)?otherword/I Capturing subpattern count = 8 Partial matching not supported +Contains explicit CR or LF match No options First char = 'w' Need char = 'd' -/.*X/D +/.*X/IDZ ------------------------------------------------------------------ - 0 7 Bra 0 - 3 Any* - 5 X - 7 7 Ket - 10 End + Bra + Any* + X + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -1125,13 +1123,13 @@ First char at start or follows newline Need char = 'X' -/.*X/Ds +/.*X/IDZs ------------------------------------------------------------------ - 0 7 Bra 0 - 3 Any* - 5 X - 7 7 Ket - 10 End + Bra + AllAny* + X + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -1139,18 +1137,18 @@ No first char Need char = 'X' -/(.*X|^B)/D +/(.*X|^B)/IDZ ------------------------------------------------------------------ - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End + Bra + CBra 1 + Any* + X + Alt + ^ + B + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -1158,37 +1156,37 @@ First char at start or follows newline No need char -/(.*X|^B)/Ds +/(.*X|^B)/IDZs ------------------------------------------------------------------ - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End + Bra + CBra 1 + AllAny* + X + Alt + ^ + B + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported Options: anchored dotall No first char No need char - -/(?s)(.*X|^B)/D + +/(?s)(.*X|^B)/IDZ ------------------------------------------------------------------ - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End + Bra + CBra 1 + AllAny* + X + Alt + ^ + B + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -1196,29 +1194,29 @@ No first char No need char -/(?s:.*X|^B)/D +/(?s:.*X|^B)/IDZ ------------------------------------------------------------------ - 0 25 Bra 0 - 3 9 Bra 0 - 6 04 Opt - 8 Any* - 10 X - 12 8 Alt - 15 04 Opt - 17 ^ - 18 B - 20 17 Ket - 23 00 Opt - 25 25 Ket - 28 End + Bra + Bra + 04 Opt + AllAny* + X + Alt + 04 Opt + ^ + B + Ket + 00 Opt + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported -No options -First char at start or follows newline +Options: anchored +No first char No need char -/\Biss\B/+ +/\Biss\B/I+ Capturing subpattern count = 0 No options First char = 'i' @@ -1227,12 +1225,12 @@ 0: iss 0+ issippi -/\Biss\B/+P +/\Biss\B/I+P Mississippi 0: iss 0+ issippi -/iss/G+ +/iss/IG+ Capturing subpattern count = 0 No options First char = 'i' @@ -1243,7 +1241,7 @@ 0: iss 0+ ippi -/\Biss\B/G+ +/\Biss\B/IG+ Capturing subpattern count = 0 No options First char = 'i' @@ -1252,7 +1250,7 @@ 0: iss 0+ issippi -/\Biss\B/g+ +/\Biss\B/Ig+ Capturing subpattern count = 0 No options First char = 'i' @@ -1267,7 +1265,7 @@ Mississippi\A No match -/(?<=[Ms])iss/g+ +/(?<=[Ms])iss/Ig+ Capturing subpattern count = 0 No options First char = 'i' @@ -1278,7 +1276,7 @@ 0: iss 0+ ippi -/(?<=[Ms])iss/G+ +/(?<=[Ms])iss/IG+ Capturing subpattern count = 0 No options First char = 'i' @@ -1287,7 +1285,7 @@ 0: iss 0+ issippi -/^iss/g+ +/^iss/Ig+ Capturing subpattern count = 0 Options: anchored No first char @@ -1295,20 +1293,20 @@ ississippi 0: iss 0+ issippi - -/.*iss/g+ + +/.*iss/Ig+ Capturing subpattern count = 0 Partial matching not supported No options First char at start or follows newline Need char = 's' - abciss\nxyzisspqr + abciss\nxyzisspqr 0: abciss 0+ \x0axyzisspqr 0: xyziss 0+ pqr -/.i./+g +/.i./I+g Capturing subpattern count = 0 No options No first char @@ -1334,11 +1332,11 @@ 0+ river 0: riv 0+ er - Missouri river\A + Missouri river\A 0: Mis 0+ souri river -/^.is/+g +/^.is/I+g Capturing subpattern count = 0 Options: anchored No first char @@ -1347,8 +1345,9 @@ 0: Mis 0+ sissippi -/^ab\n/g+ +/^ab\n/Ig+ Capturing subpattern count = 0 +Contains explicit CR or LF match Options: anchored No first char No need char @@ -1356,8 +1355,9 @@ 0: ab\x0a 0+ ab\x0acd -/^ab\n/mg+ +/^ab\n/Img+ Capturing subpattern count = 0 +Contains explicit CR or LF match Options: multiline First char at start or follows newline Need char = 10 @@ -1367,272 +1367,272 @@ 0: ab\x0a 0+ cd -/abc/ +/abc/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'c' -/abc|bac/ +/abc|bac/I Capturing subpattern count = 0 No options No first char Need char = 'c' -/(abc|bac)/ +/(abc|bac)/I Capturing subpattern count = 1 No options No first char Need char = 'c' -/(abc|(c|dc))/ +/(abc|(c|dc))/I Capturing subpattern count = 2 No options No first char Need char = 'c' -/(abc|(d|de)c)/ +/(abc|(d|de)c)/I Capturing subpattern count = 2 No options No first char Need char = 'c' -/a*/ +/a*/I Capturing subpattern count = 0 Partial matching not supported No options No first char No need char -/a+/ +/a+/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/(baa|a+)/ +/(baa|a+)/I Capturing subpattern count = 1 Partial matching not supported No options No first char Need char = 'a' -/a{0,3}/ +/a{0,3}/I Capturing subpattern count = 0 Partial matching not supported No options No first char No need char -/baa{3,}/ +/baa{3,}/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'b' Need char = 'a' -/"([^\\"]+|\\.)*"/ +/"([^\\"]+|\\.)*"/I Capturing subpattern count = 1 Partial matching not supported No options First char = '"' Need char = '"' -/(abc|ab[cd])/ +/(abc|ab[cd])/I Capturing subpattern count = 1 No options First char = 'a' No need char -/(a|.)/ +/(a|.)/I Capturing subpattern count = 1 No options No first char No need char -/a|ba|\w/ +/a|ba|\w/I Capturing subpattern count = 0 No options No first char No need char -/abc(?=pqr)/ +/abc(?=pqr)/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'r' -/...(?<=abc)/ +/...(?<=abc)/I Capturing subpattern count = 0 No options No first char No need char -/abc(?!pqr)/ +/abc(?!pqr)/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'c' -/ab./ +/ab./I Capturing subpattern count = 0 No options First char = 'a' Need char = 'b' -/ab[xyz]/ +/ab[xyz]/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'b' -/abc*/ +/abc*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'b' -/ab.c*/ +/ab.c*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'b' -/a.c*/ +/a.c*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/.c*/ +/.c*/I Capturing subpattern count = 0 Partial matching not supported No options No first char No need char -/ac*/ +/ac*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/(a.c*|b.c*)/ +/(a.c*|b.c*)/I Capturing subpattern count = 1 Partial matching not supported No options No first char No need char -/a.c*|aba/ +/a.c*|aba/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/.+a/ +/.+a/I Capturing subpattern count = 0 Partial matching not supported No options No first char Need char = 'a' -/(?=abcda)a.*/ +/(?=abcda)a.*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'a' -/(?=a)a.*/ +/(?=a)a.*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/a(b)*/ +/a(b)*/I Capturing subpattern count = 1 No options First char = 'a' No need char -/a\d*/ +/a\d*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' No need char -/ab\d*/ +/ab\d*/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'b' -/a(\d)*/ +/a(\d)*/I Capturing subpattern count = 1 No options First char = 'a' No need char -/abcde{0,0}/ +/abcde{0,0}/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'd' -/ab\d+/ +/ab\d+/I Capturing subpattern count = 0 Partial matching not supported No options First char = 'a' Need char = 'b' -/a(?(1)b)/ -Capturing subpattern count = 0 +/a(?(1)b)(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/a(?(1)bag|big)/ -Capturing subpattern count = 0 +/a(?(1)bag|big)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'g' -/a(?(1)bag|big)*/ -Capturing subpattern count = 0 +/a(?(1)bag|big)*(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/a(?(1)bag|big)+/ -Capturing subpattern count = 0 +/a(?(1)bag|big)+(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'g' -/a(?(1)b..|b..)/ -Capturing subpattern count = 0 +/a(?(1)b..|b..)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'b' -/ab\d{0}e/ +/ab\d{0}e/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'e' -/a?b?/ +/a?b?/I Capturing subpattern count = 0 No options No first char @@ -1647,10 +1647,10 @@ 0: *** Failers 0: - \N + \N No match - -/|-/ + +/|-/I Capturing subpattern count = 0 No options No first char @@ -1663,10 +1663,10 @@ 0: - *** Failers 0: - \Nabc + \Nabc No match -/a*(b+)(z)(z)/P +/a*(b+)(z)(z)/IP aaaabbbbzzzz 0: aaaabbbbzz 1: bbbb @@ -1692,8 +1692,8 @@ 1: bbbb 2: z 3: z - -/^.?abcd/S + +/^.?abcd/IS Capturing subpattern count = 0 Options: anchored No first char @@ -1707,7 +1707,7 @@ (?R) # Recurse - i.e. nested bracketed string )* # Zero or more contents \) # Closing ) - /x + /Ix Capturing subpattern count = 0 Partial matching not supported Options: extended @@ -1719,30 +1719,30 @@ 0: (abcd) xyz(abcd) 0: (abcd) - (ab(xy)cd)pqr + (ab(xy)cd)pqr 0: (ab(xy)cd) - (ab(xycd)pqr + (ab(xycd)pqr 0: (xycd) - () abc () + () abc () 0: () 12(abcde(fsh)xyz(foo(bar))lmno)89 0: (abcde(fsh)xyz(foo(bar))lmno) *** Failers No match - abcd + abcd No match abcd) No match - (abcd + (abcd No match -/\( ( (?>[^()]+) | (?R) )* \) /xg +/\( ( (?>[^()]+) | (?R) )* \) /Ixg Capturing subpattern count = 1 Partial matching not supported Options: extended First char = '(' Need char = ')' - (ab(xy)cd)pqr + (ab(xy)cd)pqr 0: (ab(xy)cd) 1: cd 1(abcd)(x(y)z)pqr @@ -1751,7 +1751,7 @@ 0: (x(y)z) 1: z -/\( (?: (?>[^()]+) | (?R) ) \) /x +/\( (?: (?>[^()]+) | (?R) ) \) /Ix Capturing subpattern count = 0 Partial matching not supported Options: extended @@ -1761,16 +1761,16 @@ 0: (abcd) (ab(xy)cd) 0: (xy) - (a(b(c)d)e) + (a(b(c)d)e) 0: (c) - ((ab)) + ((ab)) 0: ((ab)) *** Failers No match - () + () No match -/\( (?: (?>[^()]+) | (?R) )? \) /x +/\( (?: (?>[^()]+) | (?R) )? \) /Ix Capturing subpattern count = 0 Partial matching not supported Options: extended @@ -1781,7 +1781,7 @@ 12(abcde(fsh)xyz(foo(bar))lmno)89 0: (fsh) -/\( ( (?>[^()]+) | (?R) )* \) /x +/\( ( (?>[^()]+) | (?R) )* \) /Ix Capturing subpattern count = 1 Partial matching not supported Options: extended @@ -1791,7 +1791,7 @@ 0: (ab(xy)cd) 1: cd -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x +/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 2 Partial matching not supported Options: extended @@ -1802,7 +1802,7 @@ 1: ab(xy)cd 2: cd -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported Options: extended @@ -1819,7 +1819,7 @@ 2: ab(xy)cd 3: cd -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported Options: extended @@ -1836,7 +1836,7 @@ 2: 123 3: cd -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix Capturing subpattern count = 11 Partial matching not supported Options: extended @@ -1856,7 +1856,7 @@ 10: ab(xy)cd 11: cd -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported Options: extended @@ -1868,7 +1868,7 @@ 2: 123 3: <unset> -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported Options: extended @@ -1885,58 +1885,58 @@ 2: ij 3: (cd(ef)gh) -/^[[:alnum:]]/D +/^[[:alnum:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Za-z] - 37 37 Ket - 40 End + Bra + ^ + [0-9A-Za-z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^alnum:]]/D +/^[[:^alnum:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-/:-@[-`{-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x00-/:-@[-`{-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:alpha:]]/D +/^[[:alpha:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [A-Za-z] - 37 37 Ket - 40 End + Bra + ^ + [A-Za-z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^alpha:]]/D +/^[[:^alpha:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-@[-`{-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x00-@[-`{-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char - + /[_[:alpha:]]/IS Capturing subpattern count = 0 No options @@ -1945,52 +1945,52 @@ Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z -/^[[:ascii:]]/D +/^[[:ascii:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x7f] - 37 37 Ket - 40 End + Bra + ^ + [\x00-\x7f] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^ascii:]]/D +/^[[:^ascii:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x80-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x80-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:blank:]]/D +/^[[:blank:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x09 ] - 37 37 Ket - 40 End + Bra + ^ + [\x09 ] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^blank:]]/D +/^[[:^blank:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x08\x0a-\x1f!-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x00-\x08\x0a-\x1f!-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored @@ -1999,222 +1999,223 @@ /[\n\x0b\x0c\x0d[:blank:]]/IS Capturing subpattern count = 0 +Contains explicit CR or LF match No options No first char No need char Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 -/^[[:cntrl:]]/D +/^[[:cntrl:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x1f\x7f] - 37 37 Ket - 40 End + Bra + ^ + [\x00-\x1f\x7f] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:digit:]]/D +/^[[:digit:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [0-9] - 37 37 Ket - 40 End + Bra + ^ + [0-9] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:graph:]]/D +/^[[:graph:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [!-~] - 37 37 Ket - 40 End + Bra + ^ + [!-~] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:lower:]]/D +/^[[:lower:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [a-z] - 37 37 Ket - 40 End + Bra + ^ + [a-z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:print:]]/D +/^[[:print:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [ -~] - 37 37 Ket - 40 End + Bra + ^ + [ -~] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:punct:]]/D +/^[[:punct:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [!-/:-@[-`{-~] - 37 37 Ket - 40 End + Bra + ^ + [!-/:-@[-`{-~] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:space:]]/D +/^[[:space:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x09-\x0d ] - 37 37 Ket - 40 End + Bra + ^ + [\x09-\x0d ] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:upper:]]/D +/^[[:upper:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [A-Z] - 37 37 Ket - 40 End + Bra + ^ + [A-Z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:xdigit:]]/D +/^[[:xdigit:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Fa-f] - 37 37 Ket - 40 End + Bra + ^ + [0-9A-Fa-f] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:word:]]/D +/^[[:word:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Z_a-z] - 37 37 Ket - 40 End + Bra + ^ + [0-9A-Z_a-z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^cntrl:]]/D +/^[[:^cntrl:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [ -~\x80-\xff] - 37 37 Ket - 40 End + Bra + ^ + [ -~\x80-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[12[:^digit:]]/D +/^[12[:^digit:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-/12:-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x00-/12:-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/^[[:^blank:]]/D +/^[[:^blank:]]/DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x08\x0a-\x1f!-\xff] - 37 37 Ket - 40 End + Bra + ^ + [\x00-\x08\x0a-\x1f!-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored No first char No need char -/[01[:alpha:]%]/D +/[01[:alpha:]%]/DZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [%01A-Za-z] - 36 36 Ket - 39 End + Bra + [%01A-Za-z] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[[.ch.]]/ +/[[.ch.]]/I Failed: POSIX collating elements are not supported at offset 1 -/[[=ch=]]/ +/[[=ch=]]/I Failed: POSIX collating elements are not supported at offset 1 -/[[:rhubarb:]]/ +/[[:rhubarb:]]/I Failed: unknown POSIX class name at offset 3 -/[[:upper:]]/i +/[[:upper:]]/Ii Capturing subpattern count = 0 Options: caseless No first char No need char A 0: A - a + a 0: a - -/[[:lower:]]/i + +/[[:lower:]]/Ii Capturing subpattern count = 0 Options: caseless No first char No need char A 0: A - a + a 0: a -/((?-i)[[:lower:]])[[:lower:]]/i +/((?-i)[[:lower:]])[[:lower:]]/Ii Capturing subpattern count = 1 Options: caseless No first char @@ -2230,22 +2231,22 @@ 1: a Ab No match - AB + AB No match -/[\200-\110]/ +/[\200-\110]/I Failed: range out of order in character class at offset 9 -/^(?(0)f|b)oo/ +/^(?(0)f|b)oo/I Failed: invalid condition (?(0) at offset 6 -/This one's here because of the large output vector needed/ +/This one's here because of the large output vector needed/I Capturing subpattern count = 0 No options First char = 'T' Need char = 'd' -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I Capturing subpattern count = 271 Max back reference = 270 Partial matching not supported @@ -2526,13 +2527,13 @@ 270: ABC 271: ABC -/This one's here because Perl does this differently and PCRE can't at present/ +/This one's here because Perl does this differently and PCRE can't at present/I Capturing subpattern count = 0 No options First char = 'T' Need char = 't' -/(main(O)?)+/ +/(main(O)?)+/I Capturing subpattern count = 2 No options First char = 'm' @@ -2544,14 +2545,14 @@ 0: mainOmain 1: main 2: O - -/These are all cases where Perl does it differently (nested captures)/ + +/These are all cases where Perl does it differently (nested captures)/I Capturing subpattern count = 1 No options First char = 'T' Need char = 's' -/^(a(b)?)+$/ +/^(a(b)?)+$/I Capturing subpattern count = 2 Options: anchored No first char @@ -2560,197 +2561,195 @@ 0: aba 1: a 2: b - -/^(aa(bb)?)+$/ + +/^(aa(bb)?)+$/I Capturing subpattern count = 2 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: aa 2: bb - -/^(aa|aa(bb))+$/ + +/^(aa|aa(bb))+$/I Capturing subpattern count = 2 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: aa 2: bb - -/^(aa(bb)??)+$/ + +/^(aa(bb)??)+$/I Capturing subpattern count = 2 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: aa 2: bb - -/^(?:aa(bb)?)+$/ + +/^(?:aa(bb)?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: bb - -/^(aa(b(b))?)+$/ + +/^(aa(b(b))?)+$/I Capturing subpattern count = 3 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: aa 2: bb 3: b -/^(?:aa(b(b))?)+$/ +/^(?:aa(b(b))?)+$/I Capturing subpattern count = 2 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: bb 2: b -/^(?:aa(b(?:b))?)+$/ +/^(?:aa(b(?:b))?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: bb -/^(?:aa(bb(?:b))?)+$/ +/^(?:aa(bb(?:b))?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbbaa + aabbbaa 0: aabbbaa 1: bbb - -/^(?:aa(b(?:bb))?)+$/ + +/^(?:aa(b(?:bb))?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbbaa + aabbbaa 0: aabbbaa 1: bbb -/^(?:aa(?:b(b))?)+$/ +/^(?:aa(?:b(b))?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbaa + aabbaa 0: aabbaa 1: b -/^(?:aa(?:b(bb))?)+$/ +/^(?:aa(?:b(bb))?)+$/I Capturing subpattern count = 1 Options: anchored No first char No need char - aabbbaa + aabbbaa 0: aabbbaa 1: bb -/^(aa(b(bb))?)+$/ +/^(aa(b(bb))?)+$/I Capturing subpattern count = 3 Options: anchored No first char No need char - aabbbaa + aabbbaa 0: aabbbaa 1: aa 2: bbb 3: bb -/^(aa(bb(bb))?)+$/ +/^(aa(bb(bb))?)+$/I Capturing subpattern count = 3 Options: anchored No first char No need char - aabbbbaa + aabbbbaa 0: aabbbbaa 1: aa 2: bbbb 3: bb -/--------------------------------------------------------------------/ +/--------------------------------------------------------------------/I Capturing subpattern count = 0 No options First char = '-' Need char = '-' - -/#/xMD -Memory allocation (code space): 7 + +/#/IxDZ ------------------------------------------------------------------ - 0 3 Bra 0 - 3 3 Ket - 6 End + Bra + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: extended No first char No need char -/a#/xMD -Memory allocation (code space): 9 +/a#/IxDZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 a - 5 5 Ket - 8 End + Bra + a + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: extended First char = 'a' No need char -/[\s]/D +/[\s]/DZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x09\x0a\x0c\x0d ] - 36 36 Ket - 39 End + Bra + [\x09\x0a\x0c\x0d ] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[\S]/D +/[\S]/DZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x00-\x08\x0b\x0e-\x1f!-\xff] - 36 36 Ket - 39 End + Bra + [\x00-\x08\x0b\x0e-\x1f!-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/a(?i)b/D +/a(?i)b/DZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 a - 5 01 Opt - 7 NC b - 9 9 Ket - 12 End + Bra + a + 01 Opt + NC b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -2760,22 +2759,22 @@ 0: ab aB 0: aB - *** Failers + *** Failers No match - AB + AB No match -/(a(?i)b)/D +/(a(?i)b)/DZ ------------------------------------------------------------------ - 0 17 Bra 0 - 3 9 Bra 1 - 6 a - 8 01 Opt - 10 NC b - 12 9 Ket - 15 00 Opt - 17 17 Ket - 20 End + Bra + CBra 1 + a + 01 Opt + NC b + Ket + 00 Opt + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options @@ -2787,17 +2786,17 @@ aB 0: aB 1: aB - *** Failers + *** Failers No match - AB + AB No match - -/ (?i)abc/xD + +/ (?i)abc/IxDZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 NC abc - 9 9 Ket - 12 End + Bra + NC abc + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless extended @@ -2805,47 +2804,47 @@ Need char = 'c' (caseless) /#this is a comment - (?i)abc/xD + (?i)abc/IxDZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 NC abc - 9 9 Ket - 12 End + Bra + NC abc + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless extended First char = 'a' (caseless) Need char = 'c' (caseless) -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------ - 0 603 Bra 0 - 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -603 603 Ket -606 End + Bra + 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = '1' Need char = '0' -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------ - 0 603 Bra 0 - 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -603 603 Ket -606 End + Bra + 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = '1' Need char = '0' -/\Q\E/D +/\Q\E/DZ ------------------------------------------------------------------ - 0 3 Bra 0 - 3 3 Ket - 6 End + Bra + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -2854,36 +2853,36 @@ \ 0: -/\Q\Ex/D +/\Q\Ex/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 x - 5 5 Ket - 8 End + Bra + x + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = 'x' No need char -/ \Q\E/D +/ \Q\E/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 - 5 5 Ket - 8 End + Bra + + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = ' ' No need char -/a\Q\E/D +/a\Q\E/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 a - 5 5 Ket - 8 End + Bra + a + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -2893,15 +2892,15 @@ 0: a bca 0: a - bac + bac 0: a -/a\Q\Eb/D +/a\Q\Eb/DZ ------------------------------------------------------------------ - 0 7 Bra 0 - 3 ab - 7 7 Ket - 10 End + Bra + ab + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -2910,27 +2909,25 @@ abc 0: ab -/\Q\Eabc/D +/\Q\Eabc/DZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 abc - 9 9 Ket - 12 End + Bra + abc + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = 'a' Need char = 'c' -/x*+\w/D +/x*+\w/DZ ------------------------------------------------------------------ - 0 12 Bra 0 - 3 5 Once - 6 x* - 8 5 Ket - 11 \w - 12 12 Ket - 15 End + Bra + x*+ + \w + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -2941,29 +2938,25 @@ 0: F xxxxx No match - -/x?+/D + +/x?+/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 5 Once - 6 x? - 8 5 Ket - 11 11 Ket - 14 End + Bra + x?+ + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/x++/D +/x++/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 5 Once - 6 x+ - 8 5 Ket - 11 11 Ket - 14 End + Bra + x++ + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -2971,15 +2964,15 @@ First char = 'x' No need char -/x{1,3}+/D +/x{1,3}+/DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 9 Once - 6 x - 8 x{,2} - 12 9 Ket - 15 15 Ket - 18 End + Bra + Once + x + x{0,2} + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -2987,24 +2980,24 @@ First char = 'x' No need char -/(x)*+/D +/(x)*+/DZ ------------------------------------------------------------------ - 0 18 Bra 0 - 3 12 Once - 6 Brazero - 7 5 Bra 1 - 10 x - 12 5 KetRmax - 15 12 Ket - 18 18 Ket - 21 End + Bra + Once + Brazero + CBra 1 + x + KetRmax + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options No first char No need char -/^(\w++|\s++)*$/ +/^(\w++|\s++)*$/I Capturing subpattern count = 1 Partial matching not supported Options: anchored @@ -3017,8 +3010,8 @@ No match this is not a line with only words and spaces! No match - -/(\d++)(\w)/ + +/(\d++)(\w)/I Capturing subpattern count = 2 Partial matching not supported No options @@ -3030,10 +3023,10 @@ 2: a *** Failers No match - 12345+ + 12345+ No match -/a++b/ +/a++b/I Capturing subpattern count = 0 Partial matching not supported No options @@ -3042,7 +3035,7 @@ aaab 0: aaab -/(a++b)/ +/(a++b)/I Capturing subpattern count = 1 Partial matching not supported No options @@ -3052,7 +3045,7 @@ 0: aaab 1: aaab -/(a++)b/ +/(a++)b/I Capturing subpattern count = 1 Partial matching not supported No options @@ -3062,7 +3055,7 @@ 0: aaab 1: aaa -/([^()]++|\([^()]*\))+/ +/([^()]++|\([^()]*\))+/I Capturing subpattern count = 1 Partial matching not supported No options @@ -3071,8 +3064,8 @@ ((abc(ade)ufh()()x 0: abc(ade)ufh()()x 1: x - -/\(([^()]++|\([^()]+\))+\)/ + +/\(([^()]++|\([^()]+\))+\)/I Capturing subpattern count = 1 Partial matching not supported No options @@ -3086,57 +3079,55 @@ 1: xyz *** Failers No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa No match -/(abc){1,3}+/D +/(abc){1,3}+/DZ ------------------------------------------------------------------ - 0 53 Bra 0 - 3 47 Once - 6 9 Bra 1 - 9 abc - 15 9 Ket - 18 Brazero - 19 28 Bra 0 - 22 9 Bra 1 - 25 abc - 31 9 Ket - 34 Brazero - 35 9 Bra 1 - 38 abc - 44 9 Ket - 47 28 Ket - 50 47 Ket - 53 53 Ket - 56 End + Bra + Once + CBra 1 + abc + Ket + Brazero + Bra + CBra 1 + abc + Ket + Brazero + CBra 1 + abc + Ket + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options First char = 'a' Need char = 'c' -/a+?+/ +/a+?+/I Failed: nothing to repeat at offset 3 -/a{2,3}?+b/ +/a{2,3}?+b/I Failed: nothing to repeat at offset 7 -/(?U)a+?+/ +/(?U)a+?+/I Failed: nothing to repeat at offset 7 -/a{2,3}?+b/U +/a{2,3}?+b/IU Failed: nothing to repeat at offset 7 -/x(?U)a++b/D +/x(?U)a++b/DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 x - 5 5 Once - 8 a+ - 10 5 Ket - 13 b - 15 15 Ket - 18 End + Bra + x + a++ + b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -3146,16 +3137,14 @@ xaaaab 0: xaaaab -/(?U)xa++b/D +/(?U)xa++b/DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 x - 5 5 Once - 8 a+ - 10 5 Ket - 13 b - 15 15 Ket - 18 End + Bra + x + a++ + b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -3165,26 +3154,26 @@ xaaaab 0: xaaaab -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ ------------------------------------------------------------------ - 0 106 Bra 0 - 3 ^ - 4 99 Bra 1 - 7 5 Bra 2 - 10 a+ - 12 5 Ket - 15 37 Bra 3 - 18 [ab]+? - 52 37 Ket - 55 37 Bra 4 - 58 [bc]+ - 92 37 Ket - 95 5 Bra 5 - 98 \w* -100 5 Ket -103 99 Ket -106 106 Ket -109 End + Bra + ^ + CBra 1 + CBra 2 + a+ + Ket + CBra 3 + [ab]+? + Ket + CBra 4 + [bc]+ + Ket + CBra 5 + \w* + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 5 Partial matching not supported @@ -3192,15 +3181,15 @@ No first char No need char -/^x(?U)a+b/D +/^x(?U)a+b/DZ ------------------------------------------------------------------ - 0 10 Bra 0 - 3 ^ - 4 x - 6 a+? - 8 b - 10 10 Ket - 13 End + Bra + ^ + x + a++ + b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -3208,17 +3197,17 @@ No first char Need char = 'b' -/^x(?U)(a+)b/D +/^x(?U)(a+)b/DZ ------------------------------------------------------------------ - 0 16 Bra 0 - 3 ^ - 4 x - 6 5 Bra 1 - 9 a+? - 11 5 Ket - 14 b - 16 16 Ket - 19 End + Bra + ^ + x + CBra 1 + a+? + Ket + b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -3226,79 +3215,76 @@ No first char Need char = 'b' -/[.x.]/ +/[.x.]/I Failed: POSIX collating elements are not supported at offset 0 -/[=x=]/ +/[=x=]/I Failed: POSIX collating elements are not supported at offset 0 -/[:x:]/ +/[:x:]/I Failed: POSIX named classes are supported only within a class at offset 0 -/\l/ +/\l/I Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 -/\L/ +/\L/I Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 -/\N{name}/ +/\N{name}/I Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 -/\u/ +/\u/I Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 -/\U/ +/\U/I Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 -/[/ +/[/I Failed: missing terminating ] for character class at offset 1 -/[a-/ +/[a-/I Failed: missing terminating ] for character class at offset 3 -/[[:space:]/ +/[[:space:]/I Failed: missing terminating ] for character class at offset 10 -/[\s]/DM -Memory allocation (code space): 40 +/[\s]/IDZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x09\x0a\x0c\x0d ] - 36 36 Ket - 39 End + Bra + [\x09\x0a\x0c\x0d ] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[[:space:]]/DM -Memory allocation (code space): 40 +/[[:space:]]/IDZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x09-\x0d ] - 36 36 Ket - 39 End + Bra + [\x09-\x0d ] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[[:space:]abcde]/DM -Memory allocation (code space): 40 +/[[:space:]abcde]/IDZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x09-\x0d a-e] - 36 36 Ket - 39 End + Bra + [\x09-\x0d a-e] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix Capturing subpattern count = 0 Partial matching not supported Options: extended @@ -3312,37 +3298,35 @@ 0: <abc <123> hij> <abc <def> hij> 0: <def> - <abc<>def> + <abc<>def> 0: <abc<>def> - <abc<> + <abc<> 0: <> *** Failers No match <abc No match -|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM -Memory allocation (code space): 826 +|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------ - 0 822 Bra 0 - 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -821 \b -822 822 Ket -825 End + Bra + 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X + \b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = '8' Need char = 'X' -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM -Memory allocation (code space): 816 +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------ - 0 812 Bra 0 - 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -811 \b -812 812 Ket -815 End + Bra + $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X + \b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -3363,7 +3347,7 @@ No options First char at start or follows newline No need char - + /(.*)\d+\1/Is Capturing subpattern count = 1 Max back reference = 1 @@ -3398,7 +3382,7 @@ 0: bc123bc 1: bc 2: bc - + /a[b]/I Capturing subpattern count = 0 No options @@ -3412,7 +3396,7 @@ First char = 'a' No need char -/(?=abc).xyz/iI +/(?=abc).xyz/IiI Capturing subpattern count = 0 Options: caseless First char = 'a' (caseless) @@ -3454,26 +3438,26 @@ No first char Need char = 'a' -/(?(1)ab|ac)/I -Capturing subpattern count = 0 +/(?(1)ab|ac)(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/(?(1)abz|acz)/I -Capturing subpattern count = 0 +/(?(1)abz|acz)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'z' -/(?(1)abz)/I -Capturing subpattern count = 0 +/(?(1)abz)(.)/I +Capturing subpattern count = 1 No options No first char No need char -/(?(1)abz)123/I -Capturing subpattern count = 0 +/(?(1)abz)(1)23/I +Capturing subpattern count = 1 No options No first char Need char = '3' @@ -3540,18 +3524,18 @@ First char = 'a' Need char = 'b' -/^a/mI +/^a/Im Capturing subpattern count = 0 Options: multiline First char at start or follows newline Need char = 'a' abcde 0: a - xy\nabc + xy\nabc 0: a - *** Failers + *** Failers No match - xyabc + xyabc No match /c|abc/I @@ -3574,7 +3558,7 @@ Need char = 'd' (caseless) Starting byte set: a b -/abc(?C)def/ +/abc(?C)def/I Capturing subpattern count = 0 No options First char = 'a' @@ -3583,7 +3567,7 @@ --->abcdef 0 ^ ^ d 0: abcdef - 1234abcdef + 1234abcdef --->1234abcdef 0 ^ ^ d 0: abcdef @@ -3591,12 +3575,12 @@ No match abcxyz No match - abcxyzf + abcxyzf --->abcxyzf 0 ^ ^ d No match -/abc(?C)de(?C1)f/ +/abc(?C)de(?C1)f/I Capturing subpattern count = 0 No options First char = 'a' @@ -3606,8 +3590,8 @@ 0 ^ ^ d 1 ^ ^ f 0: abcdef - -/(?C1)\dabc(?C2)def/ + +/(?C1)\dabc(?C2)def/I Capturing subpattern count = 0 No options No first char @@ -3622,7 +3606,7 @@ 0: 4abcdef *** Failers No match - abcdef + abcdef --->abcdef 1 ^ \d 1 ^ \d @@ -3631,23 +3615,23 @@ 1 ^ \d 1 ^ \d No match - -/(?C255)ab/ + +/(?C255)ab/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'b' -/(?C256)ab/ +/(?C256)ab/I Failed: number after (?C is > 255 at offset 6 -/(?Cab)xx/ +/(?Cab)xx/I Failed: closing ) for (?C expected at offset 3 -/(?C12vr)x/ +/(?C12vr)x/I Failed: closing ) for (?C expected at offset 5 -/abc(?C)def/ +/abc(?C)def/I Capturing subpattern count = 0 No options First char = 'a' @@ -3659,7 +3643,7 @@ 0 ^ ^ d 0: abcdef -/(abc)(?C)de(?C1)f/ +/(abc)(?C)de(?C1)f/I Capturing subpattern count = 1 No options First char = 'a' @@ -3670,7 +3654,7 @@ 1 ^ ^ f 0: abcdef 1: abc - 123abcdef\C+ + 123abcdef\C+ Callout 0: last capture = 1 0: <unset> 1: abc @@ -3683,18 +3667,18 @@ ^ ^ f 0: abcdef 1: abc - 123abcdef\C- + 123abcdef\C- 0: abcdef 1: abc *** Failers No match - 123abcdef\C!1 + 123abcdef\C!1 --->123abcdef 0 ^ ^ d 1 ^ ^ f No match - -/(?C0)(abc(?C1))*/ + +/(?C0)(abc(?C1))*/I Capturing subpattern count = 1 No options No first char @@ -3707,7 +3691,7 @@ 1 ^ ^ ) 0: abcabcabc 1: abc - abcabc\C!1!3 + abcabc\C!1!3 --->abcabc 0 ^ (abc(?C1))* 1 ^ ^ ) @@ -3718,7 +3702,7 @@ --->*** Failers 0 ^ (abc(?C1))* 0: - abcabcabc\C!1!3 + abcabcabc\C!1!3 --->abcabcabc 0 ^ (abc(?C1))* 1 ^ ^ ) @@ -3727,7 +3711,7 @@ 0: abcabc 1: abc -/(\d{3}(?C))*/ +/(\d{3}(?C))*/I Capturing subpattern count = 1 Partial matching not supported No options @@ -3752,7 +3736,7 @@ ^ ^ ) 0: 123456 1: 456 - 123456789\C+ + 123456789\C+ Callout 0: last capture = -1 0: <unset> --->123456789 @@ -3770,7 +3754,7 @@ 0: 123456789 1: 789 -/((xyz)(?C)p|(?C1)xyzabc)/ +/((xyz)(?C)p|(?C1)xyzabc)/I Capturing subpattern count = 2 No options First char = 'x' @@ -3789,7 +3773,7 @@ 0: xyzabc 1: xyzabc -/(X)((xyz)(?C)p|(?C1)xyzabc)/ +/(X)((xyz)(?C)p|(?C1)xyzabc)/I Capturing subpattern count = 3 No options First char = 'X' @@ -3811,7 +3795,7 @@ 1: X 2: xyzabc -/(?=(abc))(?C)abcdef/ +/(?=(abc))(?C)abcdef/I Capturing subpattern count = 1 No options First char = 'a' @@ -3824,13 +3808,13 @@ ^ a 0: abcdef 1: abc - -/(?!(abc)(?C1)d)(?C2)abcxyz/ + +/(?!(abc)(?C1)d)(?C2)abcxyz/I Capturing subpattern count = 1 No options First char = 'a' Need char = 'z' - abcxyz\C+ + abcxyz\C+ Callout 1: last capture = 1 0: <unset> 1: abc @@ -3842,7 +3826,7 @@ ^ a 0: abcxyz -/(?<=(abc)(?C))xyz/ +/(?<=(abc)(?C))xyz/I Capturing subpattern count = 1 No options First char = 'x' @@ -3855,8 +3839,8 @@ ^ ) 0: xyz 1: abc - -/a(b+)(c*)(?C1)/ + +/a(b+)(c*)(?C1)/I Capturing subpattern count = 2 Partial matching not supported No options @@ -3882,7 +3866,7 @@ Callout data = 1 No match -/a(b+?)(c*?)(?C1)/ +/a(b+?)(c*?)(?C1)/I Capturing subpattern count = 2 Partial matching not supported No options @@ -3907,36 +3891,36 @@ 1 ^ ^ Callout data = 1 No match - -/(?C)abc/ + +/(?C)abc/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'c' -/(?C)^abc/ +/(?C)^abc/I Capturing subpattern count = 0 Options: anchored No first char No need char -/(?C)a|b/S +/(?C)a|b/IS Capturing subpattern count = 0 No options No first char No need char Starting byte set: a b -/(?R)/ +/(?R)/I Failed: recursive call could loop indefinitely at offset 3 -/(a|(?R))/ +/(a|(?R))/I Failed: recursive call could loop indefinitely at offset 6 -/(ab|(bc|(de|(?R))))/ +/(ab|(bc|(de|(?R))))/I Failed: recursive call could loop indefinitely at offset 15 -/x(ab|(bc|(de|(?R))))/ +/x(ab|(bc|(de|(?R))))/I Capturing subpattern count = 3 No options First char = 'x' @@ -3965,16 +3949,16 @@ 3: xxab *** Failers No match - xyab + xyab No match -/(ab|(bc|(de|(?1))))/ +/(ab|(bc|(de|(?1))))/I Failed: recursive call could loop indefinitely at offset 15 -/x(ab|(bc|(de|(?1)x)x)x)/ +/x(ab|(bc|(de|(?1)x)x)x)/I Failed: recursive call could loop indefinitely at offset 16 -/^([^()]|\((?1)*\))*$/ +/^([^()]|\((?1)*\))*$/I Capturing subpattern count = 1 Options: anchored No first char @@ -3985,15 +3969,15 @@ a(b)c 0: a(b)c 1: c - a(b(c))d + a(b(c))d 0: a(b(c))d 1: d *** Failers) No match - a(b(c)d + a(b(c)d No match -/^>abc>([^()]|\((?1)*\))*<xyz<$/ +/^>abc>([^()]|\((?1)*\))*<xyz<$/I Capturing subpattern count = 1 Options: anchored No first char @@ -4008,43 +3992,43 @@ 0: >abc>(1(2)3)<xyz< 1: (1(2)3) -/(a(?1)b)/D +/(a(?1)b)/DZ ------------------------------------------------------------------ - 0 22 Bra 0 - 3 16 Bra 1 - 6 a - 8 6 Once - 11 3 Recurse - 14 6 Ket - 17 b - 19 16 Ket - 22 22 Ket - 25 End + Bra + CBra 1 + a + Once + Recurse + Ket + b + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options First char = 'a' Need char = 'b' -/(a(?1)+b)/D +/(a(?1)+b)/DZ ------------------------------------------------------------------ - 0 22 Bra 0 - 3 16 Bra 1 - 6 a - 8 6 Once - 11 3 Recurse - 14 6 KetRmax - 17 b - 19 16 Ket - 22 22 Ket - 25 End + Bra + CBra 1 + a + Once + Recurse + KetRmax + b + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options First char = 'a' Need char = 'b' -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/i +/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/Ii Capturing subpattern count = 4 Max back reference = 4 Partial matching not supported @@ -4067,7 +4051,7 @@ 2: <unset> 3: A man, a plan, a canal: Panama 4: A - Able was I ere I saw Elba. + Able was I ere I saw Elba. 0: Able was I ere I saw Elba. 1: <unset> 2: <unset> @@ -4075,10 +4059,10 @@ 4: A *** Failers No match - The quick brown fox + The quick brown fox No match - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ + +/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I Capturing subpattern count = 2 Partial matching not supported Options: anchored @@ -4098,8 +4082,8 @@ No match ((2+2)*-3)-7) No match - -/^(x(y|(?1){2})z)/ + +/^(x(y|(?1){2})z)/I Capturing subpattern count = 2 Options: anchored No first char @@ -4108,7 +4092,7 @@ 0: xyz 1: xyz 2: y - xxyzxyzz + xxyzxyzz 0: xxyzxyzz 1: xxyzxyzz 2: xyzxyz @@ -4116,10 +4100,10 @@ No match xxyzz No match - xxyzxyzxyzz + xxyzxyzxyzz No match -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x +/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix Capturing subpattern count = 2 Partial matching not supported Options: extended @@ -4141,11 +4125,11 @@ 0: <def> 1: <def> 2: <def> - <abc<>def> + <abc<>def> 0: <abc<>def> 1: <abc<>def> 2: <abc<>def> - <abc<> + <abc<> 0: <> 1: <> 2: <> @@ -4154,13 +4138,13 @@ <abc No match -/(?1)/ +/(?1)/I Failed: reference to non-existent subpattern at offset 3 -/((?2)(abc)/ -Failed: reference to non-existent subpattern at offset 4 +/((?2)(abc)/I +Failed: missing ) at offset 10 -/^(abc)def(?1)/ +/^(abc)def(?1)/I Capturing subpattern count = 1 Options: anchored No first char @@ -4169,7 +4153,7 @@ 0: abcdefabc 1: abc -/^(a|b|c)=(?1)+/ +/^(a|b|c)=(?1)+/I Capturing subpattern count = 1 Options: anchored No first char @@ -4180,11 +4164,11 @@ a=b 0: a=b 1: a - a=bc + a=bc 0: a=bc 1: a -/^(a|b|c)=((?1))+/ +/^(a|b|c)=((?1))+/I Capturing subpattern count = 2 Options: anchored No first char @@ -4197,26 +4181,26 @@ 0: a=b 1: a 2: b - a=bc + a=bc 0: a=bc 1: a 2: c -/a(?P<name1>b|c)d(?P<longername2>e)/D +/a(?P<name1>b|c)d(?P<longername2>e)/DZ ------------------------------------------------------------------ - 0 28 Bra 0 - 3 a - 5 5 Bra 1 - 8 b - 10 5 Alt - 13 c - 15 10 Ket - 18 d - 20 5 Bra 2 - 23 e - 25 5 Ket - 28 28 Ket - 31 End + Bra + a + CBra 1 + b + Alt + c + Ket + d + CBra 2 + e + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Named capturing subpatterns: @@ -4229,28 +4213,28 @@ 0: abde 1: b 2: e - acde + acde 0: acde 1: c 2: e -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/D +/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/DZ ------------------------------------------------------------------ - 0 35 Bra 0 - 3 21 Bra 0 - 6 a - 8 13 Bra 1 - 11 c - 13 5 Bra 2 - 16 d - 18 5 Ket - 21 13 Ket - 24 21 Ket - 27 5 Bra 3 - 30 a - 32 5 Ket - 35 35 Ket - 38 End + Bra + Bra + a + CBra 1 + c + CBra 2 + d + Ket + Ket + Ket + CBra 3 + a + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 3 Named capturing subpatterns: @@ -4261,23 +4245,23 @@ First char = 'a' Need char = 'a' -/(?P<a>a)...(?P=a)bbb(?P>a)d/D +/(?P<a>a)...(?P=a)bbb(?P>a)d/DZ ------------------------------------------------------------------ - 0 34 Bra 0 - 3 5 Bra 1 - 6 a - 8 5 Ket - 11 Any - 12 Any - 13 Any - 14 \1 - 17 bbb - 23 6 Once - 26 3 Recurse - 29 6 Ket - 32 d - 34 34 Ket - 37 End + Bra + CBra 1 + a + Ket + Any + Any + Any + \1 + bbb + Once + Recurse + Ket + d + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Max back reference = 1 @@ -4287,7 +4271,7 @@ First char = 'a' Need char = 'd' -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i +/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii Capturing subpattern count = 4 Max back reference = 4 Named capturing subpatterns: @@ -4315,7 +4299,7 @@ 2: <unset> 3: A man, a plan, a canal: Panama 4: A - Able was I ere I saw Elba. + Able was I ere I saw Elba. 0: Able was I ere I saw Elba. 1: <unset> 2: <unset> @@ -4323,10 +4307,10 @@ 4: A *** Failers No match - The quick brown fox + The quick brown fox No match - -/((?(R)a|b))\1(?1)?/ + +/((?(R)a|b))\1(?1)?/I Capturing subpattern count = 1 Max back reference = 1 No options @@ -4335,18 +4319,18 @@ bb 0: bb 1: b - bbaa + bbaa 0: bba 1: b -/(.*)a/sI +/(.*)a/Is Capturing subpattern count = 1 Partial matching not supported Options: anchored dotall No first char Need char = 'a' -/(.*)a\1/sI +/(.*)a\1/Is Capturing subpattern count = 1 Max back reference = 1 Partial matching not supported @@ -4354,7 +4338,7 @@ No first char Need char = 'a' -/(.*)a(b)\2/sI +/(.*)a(b)\2/Is Capturing subpattern count = 2 Max back reference = 2 Partial matching not supported @@ -4362,14 +4346,14 @@ No first char Need char = 'b' -/((.*)a|(.*)b)z/sI +/((.*)a|(.*)b)z/Is Capturing subpattern count = 3 Partial matching not supported Options: anchored dotall No first char Need char = 'z' -/((.*)a|(.*)b)z\1/sI +/((.*)a|(.*)b)z\1/Is Capturing subpattern count = 3 Max back reference = 1 Partial matching not supported @@ -4377,7 +4361,7 @@ No first char Need char = 'z' -/((.*)a|(.*)b)z\2/sI +/((.*)a|(.*)b)z\2/Is Capturing subpattern count = 3 Max back reference = 2 Partial matching not supported @@ -4385,7 +4369,7 @@ No first char Need char = 'z' -/((.*)a|(.*)b)z\3/sI +/((.*)a|(.*)b)z\3/Is Capturing subpattern count = 3 Max back reference = 3 Partial matching not supported @@ -4393,7 +4377,7 @@ No first char Need char = 'z' -/((.*)a|^(.*)b)z\3/sI +/((.*)a|^(.*)b)z\3/Is Capturing subpattern count = 3 Max back reference = 3 Partial matching not supported @@ -4401,14 +4385,14 @@ No first char Need char = 'z' -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is Capturing subpattern count = 31 Partial matching not supported Options: anchored dotall No first char No need char -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is Capturing subpattern count = 31 Max back reference = 31 Partial matching not supported @@ -4416,7 +4400,7 @@ No first char No need char -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is Capturing subpattern count = 32 Max back reference = 32 Partial matching not supported @@ -4424,17 +4408,17 @@ No first char No need char -/(a)(bc)/ND +/(a)(bc)/INDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 5 Bra 0 - 6 a - 8 5 Ket - 11 7 Bra 0 - 14 bc - 18 7 Ket - 21 21 Ket - 24 End + Bra + Bra + a + Ket + Bra + bc + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: no_auto_capture @@ -4443,17 +4427,17 @@ abc 0: abc -/(?P<one>a)(bc)/ND +/(?P<one>a)(bc)/INDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 5 Bra 1 - 6 a - 8 5 Ket - 11 7 Bra 0 - 14 bc - 18 7 Ket - 21 21 Ket - 24 End + Bra + CBra 1 + a + Ket + Bra + bc + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Named capturing subpatterns: @@ -4465,17 +4449,17 @@ 0: abc 1: a -/(a)(?P<named>bc)/ND +/(a)(?P<named>bc)/INDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 5 Bra 0 - 6 a - 8 5 Ket - 11 7 Bra 1 - 14 bc - 18 7 Ket - 21 21 Ket - 24 End + Bra + Bra + a + Ket + CBra 1 + bc + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Named capturing subpatterns: @@ -4484,7 +4468,7 @@ First char = 'a' Need char = 'c' -/(a+)*zz/ +/(a+)*zz/I Capturing subpattern count = 1 Partial matching not supported No options @@ -4500,7 +4484,7 @@ Minimum match() recursion limit = 42 No match -/(aaa(?C1)bbb|ab)/ +/(aaa(?C1)bbb|ab)/I Capturing subpattern count = 1 No options First char = 'a' @@ -4527,7 +4511,7 @@ Callout data = -1 No match -/ab(?P<one>cd)ef(?P<two>gh)/ +/ab(?P<one>cd)ef(?P<two>gh)/I Capturing subpattern count = 2 Named capturing subpatterns: one 1 @@ -4551,22 +4535,22 @@ 2: gh C cd (2) one C gh (2) two - abcdefgh\Cthree + abcdefgh\Cthree no parentheses with name "three" 0: abcdefgh 1: cd 2: gh copy substring three failed -7 -/(?P<Tes>)(?P<Test>)/D +/(?P<Tes>)(?P<Test>)/DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 End + Bra + CBra 1 + Ket + CBra 2 + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Named capturing subpatterns: @@ -4576,15 +4560,15 @@ No first char No need char -/(?P<Test>)(?P<Tes>)/D +/(?P<Test>)(?P<Tes>)/DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 End + Bra + CBra 1 + Ket + CBra 2 + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Named capturing subpatterns: @@ -4594,7 +4578,7 @@ No first char No need char -/(?P<Z>zz)(?P<A>aa)/ +/(?P<Z>zz)(?P<A>aa)/I Capturing subpattern count = 2 Named capturing subpatterns: A 2 @@ -4613,13 +4597,13 @@ 2: aa C aa (2) A -/(?P<x>eks)(?P<x>eccs)/ -Failed: two named subpatterns have the same name at offset 16 +/(?P<x>eks)(?P<x>eccs)/I +Failed: two named subpatterns have the same name at offset 15 -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ -Failed: two named subpatterns have the same name at offset 31 +/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/I +Failed: two named subpatterns have the same name at offset 30 -"\[((?P<elem>\d+)(,(?P>elem))*)\]" +"\[((?P<elem>\d+)(,(?P>elem))*)\]"I Capturing subpattern count = 3 Named capturing subpatterns: elem 2 @@ -4634,10 +4618,10 @@ 3: ,4234 *** Failers No match - [] + [] No match -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" +"\[((?P<elem>\d+)(,(?P>elem))*)?\]"I Capturing subpattern count = 3 Named capturing subpatterns: elem 2 @@ -4650,103 +4634,103 @@ 1: 10,20,30,5,5,4,4,2,43,23,4234 2: 10 3: ,4234 - [] + [] 0: [] -/(a(b(?2)c))?/D +/(a(b(?2)c))?/DZ ------------------------------------------------------------------ - 0 31 Bra 0 - 3 Brazero - 4 24 Bra 1 - 7 a - 9 16 Bra 2 - 12 b - 14 6 Once - 17 9 Recurse - 20 6 Ket - 23 c - 25 16 Ket - 28 24 Ket - 31 31 Ket - 34 End + Bra + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 No options No first char No need char -/(a(b(?2)c))*/D +/(a(b(?2)c))*/DZ ------------------------------------------------------------------ - 0 31 Bra 0 - 3 Brazero - 4 24 Bra 1 - 7 a - 9 16 Bra 2 - 12 b - 14 6 Once - 17 9 Recurse - 20 6 Ket - 23 c - 25 16 Ket - 28 24 KetRmax - 31 31 Ket - 34 End + Bra + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + KetRmax + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 No options No first char No need char -/(a(b(?2)c)){0,2}/D +/(a(b(?2)c)){0,2}/DZ ------------------------------------------------------------------ - 0 65 Bra 0 - 3 Brazero - 4 58 Bra 0 - 7 24 Bra 1 - 10 a - 12 16 Bra 2 - 15 b - 17 6 Once - 20 12 Recurse - 23 6 Ket - 26 c - 28 16 Ket - 31 24 Ket - 34 Brazero - 35 24 Bra 1 - 38 a - 40 16 Bra 2 - 43 b - 45 6 Once - 48 12 Recurse - 51 6 Ket - 54 c - 56 16 Ket - 59 24 Ket - 62 58 Ket - 65 65 Ket - 68 End + Bra + Brazero + Bra + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 No options No first char No need char -/[ab]{1}+/D +/[ab]{1}+/DZ ------------------------------------------------------------------ - 0 47 Bra 0 - 3 41 Once - 6 [ab]{1,1} - 44 41 Ket - 47 47 Ket - 50 End + Bra + Once + [ab]{1,1} + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii Capturing subpattern count = 3 Partial matching not supported Options: caseless @@ -4756,7 +4740,7 @@ 0: Baby Bjorn Active Carrier - With free SHIPPING!! 1: Baby Bjorn Active Carrier - With free SHIPPING!! -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS Capturing subpattern count = 3 Partial matching not supported Options: caseless @@ -4766,15 +4750,15 @@ Baby Bjorn Active Carrier - With free SHIPPING!! 0: Baby Bjorn Active Carrier - With free SHIPPING!! 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/SD + +/a*.*b/ISDZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 a* - 5 Any* - 7 b - 9 9 Ket - 12 End + Bra + a* + Any* + b + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -4783,19 +4767,19 @@ Need char = 'b' Study returned NULL -/(a|b)*.?c/SD +/(a|b)*.?c/ISDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 Brazero - 4 5 Bra 1 - 7 a - 9 5 Alt - 12 b - 14 10 KetRmax - 17 Any? - 19 c - 21 21 Ket - 24 End + Bra + Brazero + CBra 1 + a + Alt + b + KetRmax + Any? + c + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 No options @@ -4803,38 +4787,38 @@ Need char = 'c' Study returned NULL -/abc(?C255)de(?C)f/D +/abc(?C255)de(?C)f/DZ ------------------------------------------------------------------ - 0 27 Bra 0 - 3 abc - 9 Callout 255 10 1 - 15 de - 19 Callout 0 16 1 - 25 f - 27 27 Ket - 30 End + Bra + abc + Callout 255 10 1 + de + Callout 0 16 1 + f + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options First char = 'a' Need char = 'f' -/abcde/CD +/abcde/ICDZ ------------------------------------------------------------------ - 0 49 Bra 0 - 3 Callout 255 0 1 - 9 a - 11 Callout 255 1 1 - 17 b - 19 Callout 255 2 1 - 25 c - 27 Callout 255 3 1 - 33 d - 35 Callout 255 4 1 - 41 e - 43 Callout 255 5 0 - 49 49 Ket - 52 End + Bra + Callout 255 0 1 + a + Callout 255 1 1 + b + Callout 255 2 1 + c + Callout 255 3 1 + d + Callout 255 4 1 + e + Callout 255 5 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: @@ -4849,7 +4833,7 @@ +4 ^ ^ e +5 ^ ^ 0: abcde - abcdfe + abcdfe --->abcdfe +0 ^ a +1 ^^ b @@ -4857,17 +4841,17 @@ +3 ^ ^ d +4 ^ ^ e No match - -/a*b/CD + +/a*b/ICDZ ------------------------------------------------------------------ - 0 25 Bra 0 - 3 Callout 255 0 2 - 9 a* - 11 Callout 255 2 1 - 17 b - 19 Callout 255 3 0 - 25 25 Ket - 28 End + Bra + Callout 255 0 2 + a*+ + Callout 255 2 1 + b + Callout 255 3 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -4886,26 +4870,16 @@ +2 ^ ^ b +3 ^ ^ 0: aaaab - aaaacb + aaaacb --->aaaacb +0 ^ a* +2 ^ ^ b - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +2 ^ b +0 ^ a* +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +2 ^ b +0 ^ a* +2 ^ ^ b - +2 ^^ b - +2 ^ b +0 ^ a* +2 ^^ b - +2 ^ b +0 ^ a* +2 ^ b +0 ^ a* @@ -4913,16 +4887,16 @@ +3 ^^ 0: b -/a+b/CD +/a+b/ICDZ ------------------------------------------------------------------ - 0 25 Bra 0 - 3 Callout 255 0 2 - 9 a+ - 11 Callout 255 2 1 - 17 b - 19 Callout 255 3 0 - 25 25 Ket - 28 End + Bra + Callout 255 0 2 + a++ + Callout 255 2 1 + b + Callout 255 3 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -4941,50 +4915,44 @@ +2 ^ ^ b +3 ^ ^ 0: aaaab - aaaacb + aaaacb --->aaaacb +0 ^ a+ +2 ^ ^ b - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b +0 ^ a+ +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b +0 ^ a+ +2 ^ ^ b - +2 ^^ b +0 ^ a+ +2 ^^ b No match -/(abc|def)x/CD +/(abc|def)x/ICDZ ------------------------------------------------------------------ - 0 92 Bra 0 - 3 Callout 255 0 9 - 9 33 Bra 1 - 12 Callout 255 1 1 - 18 a - 20 Callout 255 2 1 - 26 b - 28 Callout 255 3 1 - 34 c - 36 Callout 255 4 0 - 42 33 Alt - 45 Callout 255 5 1 - 51 d - 53 Callout 255 6 1 - 59 e - 61 Callout 255 7 1 - 67 f - 69 Callout 255 8 0 - 75 66 Ket - 78 Callout 255 9 1 - 84 x - 86 Callout 255 10 0 - 92 92 Ket - 95 End + Bra + Callout 255 0 9 + CBra 1 + Callout 255 1 1 + a + Callout 255 2 1 + b + Callout 255 3 1 + c + Callout 255 4 0 + Alt + Callout 255 5 1 + d + Callout 255 6 1 + e + Callout 255 7 1 + f + Callout 255 8 0 + Ket + Callout 255 9 1 + x + Callout 255 10 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: @@ -5049,7 +5017,7 @@ +5 ^ d No match -/(ab|cd){3,4}/C +/(ab|cd){3,4}/IC Capturing subpattern count = 1 Options: No first char @@ -5091,7 +5059,7 @@ +12 ^ ^ 0: abcdabcd 1: cd - abcdcdcdcdcd + abcdcdcdcdcd --->abcdcdcdcdcd +0 ^ (ab|cd){3,4} +1 ^ a @@ -5113,34 +5081,34 @@ 0: abcdcdcd 1: cd -/([ab]{,4}c|xy)/CD +/([ab]{,4}c|xy)/ICDZ ------------------------------------------------------------------ - 0 131 Bra 0 - 3 Callout 255 0 14 - 9 88 Bra 1 - 12 Callout 255 1 4 - 18 [ab] - 51 Callout 255 5 1 - 57 { - 59 Callout 255 6 1 - 65 , - 67 Callout 255 7 1 - 73 4 - 75 Callout 255 8 1 - 81 } - 83 Callout 255 9 1 - 89 c - 91 Callout 255 10 0 - 97 25 Alt -100 Callout 255 11 1 -106 x -108 Callout 255 12 1 -114 y -116 Callout 255 13 0 -122 113 Ket -125 Callout 255 14 0 -131 131 Ket -134 End + Bra + Callout 255 0 14 + CBra 1 + Callout 255 1 4 + [ab] + Callout 255 5 1 + { + Callout 255 6 1 + , + Callout 255 7 1 + 4 + Callout 255 8 1 + } + Callout 255 9 1 + c + Callout 255 10 0 + Alt + Callout 255 11 1 + x + Callout 255 12 1 + y + Callout 255 13 0 + Ket + Callout 255 14 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: @@ -5288,85 +5256,85 @@ +11 ^ x No match -/([ab]{1,4}c|xy){4,5}?123/CD +/([ab]{1,4}c|xy){4,5}?123/ICDZ ------------------------------------------------------------------ - 0 485 Bra 0 - 3 Callout 255 0 21 - 9 61 Bra 1 - 12 Callout 255 1 9 - 18 [ab]{1,4} - 56 Callout 255 10 1 - 62 c - 64 Callout 255 11 0 - 70 25 Alt - 73 Callout 255 12 1 - 79 x - 81 Callout 255 13 1 - 87 y - 89 Callout 255 14 0 - 95 86 Ket - 98 61 Bra 1 -101 Callout 255 1 9 -107 [ab]{1,4} -145 Callout 255 10 1 -151 c -153 Callout 255 11 0 -159 25 Alt -162 Callout 255 12 1 -168 x -170 Callout 255 13 1 -176 y -178 Callout 255 14 0 -184 86 Ket -187 61 Bra 1 -190 Callout 255 1 9 -196 [ab]{1,4} -234 Callout 255 10 1 -240 c -242 Callout 255 11 0 -248 25 Alt -251 Callout 255 12 1 -257 x -259 Callout 255 13 1 -265 y -267 Callout 255 14 0 -273 86 Ket -276 61 Bra 1 -279 Callout 255 1 9 -285 [ab]{1,4} -323 Callout 255 10 1 -329 c -331 Callout 255 11 0 -337 25 Alt -340 Callout 255 12 1 -346 x -348 Callout 255 13 1 -354 y -356 Callout 255 14 0 -362 86 Ket -365 Braminzero -366 61 Bra 1 -369 Callout 255 1 9 -375 [ab]{1,4} -413 Callout 255 10 1 -419 c -421 Callout 255 11 0 -427 25 Alt -430 Callout 255 12 1 -436 x -438 Callout 255 13 1 -444 y -446 Callout 255 14 0 -452 86 Ket -455 Callout 255 21 1 -461 1 -463 Callout 255 22 1 -469 2 -471 Callout 255 23 1 -477 3 -479 Callout 255 24 0 -485 485 Ket -488 End + Bra + Callout 255 0 21 + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + Braminzero + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + Callout 255 21 1 + 1 + Callout 255 22 1 + 2 + Callout 255 23 1 + 3 + Callout 255 24 0 + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -5407,8 +5375,8 @@ No need char ab cd\>1 0: cd - -/\b.*/Is + +/\b.*/Is Capturing subpattern count = 0 Partial matching not supported Options: dotall @@ -5416,17 +5384,17 @@ No need char ab cd\>1 0: cd - + /(?!.bcd).*/I Capturing subpattern count = 0 Partial matching not supported No options No first char No need char - Xbcd12345 + Xbcd12345 0: bcd12345 -/abcde/ +/abcde/I Capturing subpattern count = 0 No options First char = 'a' @@ -5437,7 +5405,7 @@ Partial match abcd\P Partial match - abcde\P + abcde\P 0: abcde the quick brown abc\P Partial match @@ -5445,8 +5413,8 @@ No match the quick brown abxyz fox\P No match - -"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$" + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I Capturing subpattern count = 3 Options: anchored No first char @@ -5460,7 +5428,7 @@ 1: 13 2: 5 3: 20 - 02/05/09\P + 02/05/09\P 0: 02/05/09 1: 02 2: 05 @@ -5470,7 +5438,7 @@ Partial match 1/2/0\P Partial match - 1/2/04\P + 1/2/04\P 0: 1/2/04 1: 1 2: 2 @@ -5478,7 +5446,7 @@ Partial match 02/\P Partial match - 02/0\P + 02/0\P Partial match 02/1\P Partial match @@ -5494,11 +5462,11 @@ No match 0/1/2003\P No match - 0/\P + 0/\P No match - 02/0/\P + 02/0/\P No match - 02/13\P + 02/13\P No match /0{0,2}ABC/I @@ -5507,14 +5475,14 @@ No options No first char Need char = 'C' - + /\d{3,}ABC/I Capturing subpattern count = 0 Partial matching not supported No options No first char Need char = 'C' - + /\d*ABC/I Capturing subpattern count = 0 Partial matching not supported @@ -5529,7 +5497,7 @@ No first char Need char = 'E' -/[abc]?123/ +/[abc]?123/I Capturing subpattern count = 0 No options No first char @@ -5544,10 +5512,10 @@ Partial match c12\P Partial match - c123\P + c123\P 0: c123 -/^(?:\d){3,5}X/ +/^(?:\d){3,5}X/I Capturing subpattern count = 0 Options: anchored No first char @@ -5564,16 +5532,16 @@ 0: 1234X 12345\P Partial match - 12345X + 12345X 0: 12345X - *** Failers + *** Failers No match - 1X + 1X No match - 123456\P + 123456\P No match -/abc/>testsavedregex +/abc/I>testsavedregex Capturing subpattern count = 0 No options First char = 'a' @@ -5582,18 +5550,14 @@ <testsavedregex Compiled regex loaded from testsavedregex No study data -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' abc 0: abc ** Failers No match bca No match - -/abc/F>testsavedregex + +/abc/IF>testsavedregex Capturing subpattern count = 0 No options First char = 'a' @@ -5602,10 +5566,6 @@ <testsavedregex Compiled regex (byte-inverted) loaded from testsavedregex No study data -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' abc 0: abc ** Failers @@ -5613,7 +5573,7 @@ bca No match -/(a|b)/S>testsavedregex +/(a|b)/IS>testsavedregex Capturing subpattern count = 1 No options No first char @@ -5624,21 +5584,16 @@ <testsavedregex Compiled regex loaded from testsavedregex Study data loaded from testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b abc 0: a 1: a ** Failers 0: a 1: a - def + def No match - -/(a|b)/SF>testsavedregex + +/(a|b)/ISF>testsavedregex Capturing subpattern count = 1 No options No first char @@ -5649,21 +5604,16 @@ <testsavedregex Compiled regex (byte-inverted) loaded from testsavedregex Study data loaded from testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b abc 0: a 1: a ** Failers 0: a 1: a - def + def No match - -~<(\w+)/?>(.)*</(\1)>~smg + +~<(\w+)/?>(.)*</(\1)>~smgI Capturing subpattern count = 3 Max back reference = 1 Partial matching not supported @@ -5682,59 +5632,62 @@ No first char No need char -/line\nbreak/ +/line\nbreak/I Capturing subpattern count = 0 +Contains explicit CR or LF match No options First char = 'l' Need char = 'k' this is a line\nbreak 0: line\x0abreak - line one\nthis is a line\nbreak in the second line + line one\nthis is a line\nbreak in the second line 0: line\x0abreak -/line\nbreak/f +/line\nbreak/If Capturing subpattern count = 0 +Contains explicit CR or LF match Options: firstline First char = 'l' Need char = 'k' this is a line\nbreak 0: line\x0abreak - ** Failers + ** Failers No match - line one\nthis is a line\nbreak in the second line + line one\nthis is a line\nbreak in the second line No match -/line\nbreak/mf +/line\nbreak/Imf Capturing subpattern count = 0 +Contains explicit CR or LF match Options: multiline firstline First char = 'l' Need char = 'k' this is a line\nbreak 0: line\x0abreak - ** Failers + ** Failers No match - line one\nthis is a line\nbreak in the second line + line one\nthis is a line\nbreak in the second line No match -/ab.cd/P +/ab.cd/IP ab-cd 0: ab-cd - ab=cd + ab=cd 0: ab=cd ** Failers No match: POSIX code 17: match failed ab\ncd No match: POSIX code 17: match failed -/ab.cd/Ps +/ab.cd/IPs ab-cd 0: ab-cd - ab=cd + ab=cd 0: ab=cd ab\ncd 0: ab\x0acd -/(?i)(?-i)AbCd/ +/(?i)(?-i)AbCd/I Capturing subpattern count = 0 No options First char = 'A' @@ -5743,19 +5696,19 @@ 0: AbCd ** Failers No match - abcd + abcd No match - -/a{11111111111111111111}/ + +/a{11111111111111111111}/I Failed: number too big in {} quantifier at offset 22 -/(){64294967295}/ +/(){64294967295}/I Failed: number too big in {} quantifier at offset 14 -/(){2,4294967295}/ +/(){2,4294967295}/I Failed: number too big in {} quantifier at offset 15 -"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B" +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I Capturing subpattern count = 1 Max back reference = 1 No options @@ -5765,7 +5718,7 @@ 0: abcdefghijklAkB 1: k -"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B" +"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I Capturing subpattern count = 12 Max back reference = 11 Named capturing subpatterns: @@ -5799,7 +5752,7 @@ 11: k 12: l -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B" +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I Capturing subpattern count = 12 Max back reference = 11 No options @@ -5820,7 +5773,7 @@ 11: k 12: l -"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)" +"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I Capturing subpattern count = 101 Named capturing subpatterns: name0 1 @@ -5945,7 +5898,7 @@ 13: a 14: a -"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)" +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I Capturing subpattern count = 101 No options First char = 'a' @@ -5968,7 +5921,7 @@ 13: a 14: a -/[^()]*(?:\((?R)\)[^()]*)*/ +/[^()]*(?:\((?R)\)[^()]*)*/I Capturing subpattern count = 0 Partial matching not supported No options @@ -5976,12 +5929,12 @@ No need char (this(and)that 0: - (this(and)that) + (this(and)that) 0: (this(and)that) (this(and)that)stuff 0: (this(and)that)stuff -/[^()]*(?:\((?>(?R))\)[^()]*)*/ +/[^()]*(?:\((?>(?R))\)[^()]*)*/I Capturing subpattern count = 0 Partial matching not supported No options @@ -5989,10 +5942,10 @@ No need char (this(and)that 0: - (this(and)that) + (this(and)that) 0: (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/ + +/[^()]*(?:\((?R)\))*[^()]*/I Capturing subpattern count = 0 Partial matching not supported No options @@ -6000,10 +5953,10 @@ No need char (this(and)that 0: - (this(and)that) + (this(and)that) 0: (this(and)that) -/(?:\((?R)\))*[^()]*/ +/(?:\((?R)\))*[^()]*/I Capturing subpattern count = 0 Partial matching not supported No options @@ -6011,12 +5964,12 @@ No need char (this(and)that 0: - (this(and)that) + (this(and)that) 0: - ((this)) + ((this)) 0: ((this)) -/(?:\((?R)\))|[^()]*/ +/(?:\((?R)\))|[^()]*/I Capturing subpattern count = 0 Partial matching not supported No options @@ -6024,34 +5977,34 @@ No need char (this(and)that 0: - (this(and)that) + (this(and)that) 0: (this) 0: (this) - ((this)) + ((this)) 0: ((this)) - -/a(b)c/PN + +/a(b)c/IPN abc Matched with REG_NOSUB - -/a(?P<name>b)c/PN - abc + +/a(?P<name>b)c/IPN + abc Matched with REG_NOSUB - -/\x{100}/ + +/\x{100}/I Failed: character value in \x{...} sequence is too large at offset 6 -/\x{0000ff}/ +/\x{0000ff}/I Capturing subpattern count = 0 No options First char = 255 No need char -/^((?P<A>a1)|(?P<A>a2)b)/ -Failed: two named subpatterns have the same name at offset 18 +/^((?P<A>a1)|(?P<A>a2)b)/I +Failed: two named subpatterns have the same name at offset 17 -/^((?P<A>a1)|(?P<A>a2)b)/J +/^((?P<A>a1)|(?P<A>a2)b)/IJ Capturing subpattern count = 3 Named capturing subpatterns: A 2 @@ -6064,7 +6017,7 @@ 1: a1 2: a1 C a1 (2) A - a2b\CA + a2b\CA 0: a2b 1: a2b 2: <unset> @@ -6072,15 +6025,15 @@ C a2 (2) A ** Failers No match - a1b\CZ\CA + a1b\CZ\CA no parentheses with name "Z" 0: a1 1: a1 2: a1 copy substring Z failed -7 C a1 (2) A - -/^(?P<A>a)(?P<A>b)/J + +/^(?P<A>a)(?P<A>b)/IJ Capturing subpattern count = 2 Named capturing subpatterns: A 1 @@ -6093,8 +6046,8 @@ 1: a 2: b C a (1) A - -/^(?P<A>a)(?P<A>b)|cd/J + +/^(?P<A>a)(?P<A>b)|cd/IJ Capturing subpattern count = 2 Named capturing subpatterns: A 1 @@ -6107,11 +6060,11 @@ 1: a 2: b C a (1) A - cd\CA + cd\CA 0: cd copy substring A failed -7 - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J + +/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ Capturing subpattern count = 4 Named capturing subpatterns: A 1 @@ -6121,15 +6074,15 @@ Options: dupnames No first char No need char - cdefgh\CA + cdefgh\CA 0: cdefgh 1: <unset> 2: <unset> 3: ef 4: gh C ef (2) A - -/^((?P<A>a1)|(?P<A>a2)b)/J + +/^((?P<A>a1)|(?P<A>a2)b)/IJ Capturing subpattern count = 3 Named capturing subpatterns: A 2 @@ -6142,7 +6095,7 @@ 1: a1 2: a1 G a1 (2) A - a2b\GA + a2b\GA 0: a2b 1: a2b 2: <unset> @@ -6150,15 +6103,15 @@ G a2 (2) A ** Failers No match - a1b\GZ\GA + a1b\GZ\GA no parentheses with name "Z" 0: a1 1: a1 2: a1 copy substring Z failed -7 G a1 (2) A - -/^(?P<A>a)(?P<A>b)/J + +/^(?P<A>a)(?P<A>b)/IJ Capturing subpattern count = 2 Named capturing subpatterns: A 1 @@ -6171,8 +6124,8 @@ 1: a 2: b G a (1) A - -/^(?P<A>a)(?P<A>b)|cd/J + +/^(?P<A>a)(?P<A>b)|cd/IJ Capturing subpattern count = 2 Named capturing subpatterns: A 1 @@ -6185,11 +6138,11 @@ 1: a 2: b G a (1) A - cd\GA + cd\GA 0: cd copy substring A failed -7 - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J + +/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ Capturing subpattern count = 4 Named capturing subpatterns: A 1 @@ -6199,20 +6152,21 @@ Options: dupnames No first char No need char - cdefgh\GA + cdefgh\GA 0: cdefgh 1: <unset> 2: <unset> 3: ef 4: gh G ef (2) A - -/(?J)^((?P<A>a1)|(?P<A>a2)b)/ + +/(?J)^((?P<A>a1)|(?P<A>a2)b)/I Capturing subpattern count = 3 Named capturing subpatterns: A 2 A 3 Options: anchored dupnames +Duplicate name status changes No first char No need char a1b\CA @@ -6220,25 +6174,25 @@ 1: a1 2: a1 C a1 (2) A - a2b\CA + a2b\CA 0: a2b 1: a2b 2: <unset> 3: a2 C a2 (2) A - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/ -Failed: two named subpatterns have the same name at offset 38 + +/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/I +Failed: two named subpatterns have the same name at offset 37 / In this next test, J is not set at the outer level; consequently it isn't -set in the pattern's options; consequently pcre_get_named_substring() produces -a random value. /x +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /Ix Capturing subpattern count = 1 Options: extended First char = 'I' Need char = 'e' -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/ +/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I Capturing subpattern count = 4 Named capturing subpatterns: A 1 @@ -6246,6 +6200,7 @@ B 3 C 4 Options: anchored +Duplicate name status changes No first char No need char a bc d\CA\CB\CC @@ -6258,7 +6213,7 @@ C b (1) B C d (1) C -/^(?P<A>a)?(?(A)a|b)/ +/^(?P<A>a)?(?(A)a|b)/I Capturing subpattern count = 1 Named capturing subpatterns: A 1 @@ -6272,10 +6227,10 @@ 0: b ** Failers No match - abc + abc No match -/(?:(?(ZZ)a|b)(?P<ZZ>X))+/ +/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I Capturing subpattern count = 1 Named capturing subpatterns: ZZ 1 @@ -6286,13 +6241,13 @@ 0: bXaX 1: X -/(?:(?(2y)a|b)(X))+/ +/(?:(?(2y)a|b)(X))+/I Failed: reference to non-existent subpattern at offset 9 -/(?:(?(ZA)a|b)(?P<ZZ>X))+/ +/(?:(?(ZA)a|b)(?P<ZZ>X))+/I Failed: reference to non-existent subpattern at offset 9 -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/ +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I Capturing subpattern count = 1 Named capturing subpatterns: ZZ 1 @@ -6303,7 +6258,7 @@ 0: bbXaaX 1: X -/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/ +/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I Capturing subpattern count = 1 Named capturing subpatterns: ZZ 1 @@ -6314,10 +6269,10 @@ 0: (b)\Xa\X 1: X -/(?P<ABC/ -Failed: syntax error after (?P at offset 7 +/(?P<ABC/I +Failed: syntax error in subpattern name (missing terminator) at offset 7 -/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ +/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I Capturing subpattern count = 1 Max back reference = 1 Named capturing subpatterns: @@ -6328,11 +6283,11 @@ bXXaYYaY 0: bXXaYYaY 1: Y - bXYaXXaX + bXYaXXaX 0: bX 1: X -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I Capturing subpattern count = 10 Max back reference = 10 Named capturing subpatterns: @@ -6353,10 +6308,10 @@ 9: 10: Y -/\777/ +/\777/I Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 -/\s*,\s*/S +/\s*,\s*/IS Capturing subpattern count = 0 Partial matching not supported No options @@ -6365,10 +6320,10 @@ Starting byte set: \x09 \x0a \x0c \x0d \x20 , \x0b,\x0b 0: , - \x0c,\x0d + \x0c,\x0d 0: \x0c,\x0d -/^abc/m +/^abc/Im Capturing subpattern count = 0 Options: multiline First char at start or follows newline @@ -6383,7 +6338,7 @@ 0: abc xyz\r\nabc\<crlf> 0: abc - ** Failers + ** Failers No match xyz\nabc\<cr> No match @@ -6395,38 +6350,39 @@ No match xyz\rabc\<lf> No match - -/abc$/m + +/abc$/Im<lf> Capturing subpattern count = 0 Options: multiline +Forced newline sequence: LF First char = 'a' Need char = 'c' xyzabc 0: abc - xyzabc\n + xyzabc\n 0: abc - xyzabc\npqr + xyzabc\npqr 0: abc - xyzabc\r\<cr> + xyzabc\r\<cr> 0: abc - xyzabc\rpqr\<cr> + xyzabc\rpqr\<cr> 0: abc - xyzabc\r\n\<crlf> + xyzabc\r\n\<crlf> 0: abc - xyzabc\r\npqr\<crlf> + xyzabc\r\npqr\<crlf> 0: abc ** Failers No match - xyzabc\r + xyzabc\r No match - xyzabc\rpqr + xyzabc\rpqr No match - xyzabc\r\n + xyzabc\r\n No match - xyzabc\r\npqr + xyzabc\r\npqr No match - -/^abc/m<cr> + +/^abc/Im<cr> Capturing subpattern count = 0 Options: multiline Forced newline sequence: CR @@ -6436,12 +6392,12 @@ 0: abc xyz\nabcdef\<lf> 0: abc - ** Failers + ** Failers No match xyz\nabcdef No match - -/^abc/m<lf> + +/^abc/Im<lf> Capturing subpattern count = 0 Options: multiline Forced newline sequence: LF @@ -6451,12 +6407,12 @@ 0: abc xyz\rabcdef\<cr> 0: abc - ** Failers + ** Failers No match xyz\rabcdef No match - -/^abc/m<crlf> + +/^abc/Im<crlf> Capturing subpattern count = 0 Options: multiline Forced newline sequence: CRLF @@ -6466,29 +6422,30 @@ 0: abc xyz\rabcdef\<cr> 0: abc - ** Failers + ** Failers No match xyz\rabcdef No match - -/^abc/m<bad> + +/^abc/Im<bad> Unknown newline type at: <bad> -/abc/ +/abc/I Capturing subpattern count = 0 No options First char = 'a' Need char = 'c' xyz\rabc\<bad> Unknown newline type at: <bad> - abc + abc 0: abc - -/.*/ + +/.*/I<lf> Capturing subpattern count = 0 Partial matching not supported -No options +Options: +Forced newline sequence: LF First char at start or follows newline No need char abc\ndef @@ -6510,7 +6467,7 @@ \<crlf>abc\r\ndef 0: abc -/\w+(.)(.)?def/s +/\w+(.)(.)?def/Is Capturing subpattern count = 2 Partial matching not supported Options: dotall @@ -6527,7 +6484,7 @@ 1: \x0d 2: \x0a -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+ ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I Capturing subpattern count = 1 Partial matching not supported No options @@ -6539,7 +6496,7 @@ 0: /* this is a C style comment */ 1: /* this is a C style comment */ -/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/ +/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I Capturing subpattern count = 1 Named capturing subpatterns: B 1 @@ -6547,8 +6504,3340 @@ No first char Need char = '.' -/ End of testinput2 / -Capturing subpattern count = 0 +/()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + (.(.))/Ix +Capturing subpattern count = 102 +Options: extended +No first char +No need char + XY\O400 + 0: XY + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: +11: +12: +13: +14: +15: +16: +17: +18: +19: +20: +21: +22: +23: +24: +25: +26: +27: +28: +29: +30: +31: +32: +33: +34: +35: +36: +37: +38: +39: +40: +41: +42: +43: +44: +45: +46: +47: +48: +49: +50: +51: +52: +53: +54: +55: +56: +57: +58: +59: +60: +61: +62: +63: +64: +65: +66: +67: +68: +69: +70: +71: +72: +73: +74: +75: +76: +77: +78: +79: +80: +81: +82: +83: +84: +85: +86: +87: +88: +89: +90: +91: +92: +93: +94: +95: +96: +97: +98: +99: +100: +101: XY +102: Y + +/(a*b|(?i:c*(?-i)d))/IS +Capturing subpattern count = 1 +Partial matching not supported No options -First char = ' ' -Need char = ' ' +No first char +No need char +Starting byte set: C a b c d + +/()[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b + +/(|)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b + +/(|c)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c + +/(|c?)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c + +/(d?|c?)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c d + +/(d?|c)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c d + +/^a*b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a*+b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a*?b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a+A\d/DZ +------------------------------------------------------------------ + Bra + ^ + a++ + A + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'A' + aaaA5 + 0: aaaA5 + ** Failers +No match + aaaa5 +No match + +/^a*A\d/IiDZ +------------------------------------------------------------------ + Bra + ^ + a* + NC A + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored caseless +No first char +Need char = 'A' (caseless) + aaaA5 + 0: aaaA5 + aaaa5 + 0: aaaa5 + +/(a*|b*)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a+|b*)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a*|b+)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a+|b+)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b + +/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + ((( + a + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + ))) +/Ix +Capturing subpattern count = 203 +Options: extended +First char = 'a' +No need char + large nest +Matched, but too many substrings + 0: a + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +/a*\d/BZ +------------------------------------------------------------------ + Bra + a*+ + \d + Ket + End +------------------------------------------------------------------ + +/a*\D/BZ +------------------------------------------------------------------ + Bra + a* + \D + Ket + End +------------------------------------------------------------------ + +/0*\d/BZ +------------------------------------------------------------------ + Bra + 0* + \d + Ket + End +------------------------------------------------------------------ + +/0*\D/BZ +------------------------------------------------------------------ + Bra + 0*+ + \D + Ket + End +------------------------------------------------------------------ + +/a*\s/BZ +------------------------------------------------------------------ + Bra + a*+ + \s + Ket + End +------------------------------------------------------------------ + +/a*\S/BZ +------------------------------------------------------------------ + Bra + a* + \S + Ket + End +------------------------------------------------------------------ + +/ *\s/BZ +------------------------------------------------------------------ + Bra + * + \s + Ket + End +------------------------------------------------------------------ + +/ *\S/BZ +------------------------------------------------------------------ + Bra + *+ + \S + Ket + End +------------------------------------------------------------------ + +/a*\w/BZ +------------------------------------------------------------------ + Bra + a* + \w + Ket + End +------------------------------------------------------------------ + +/a*\W/BZ +------------------------------------------------------------------ + Bra + a*+ + \W + Ket + End +------------------------------------------------------------------ + +/=*\w/BZ +------------------------------------------------------------------ + Bra + =*+ + \w + Ket + End +------------------------------------------------------------------ + +/=*\W/BZ +------------------------------------------------------------------ + Bra + =* + \W + Ket + End +------------------------------------------------------------------ + +/\d*a/BZ +------------------------------------------------------------------ + Bra + \d*+ + a + Ket + End +------------------------------------------------------------------ + +/\d*2/BZ +------------------------------------------------------------------ + Bra + \d* + 2 + Ket + End +------------------------------------------------------------------ + +/\d*\d/BZ +------------------------------------------------------------------ + Bra + \d* + \d + Ket + End +------------------------------------------------------------------ + +/\d*\D/BZ +------------------------------------------------------------------ + Bra + \d*+ + \D + Ket + End +------------------------------------------------------------------ + +/\d*\s/BZ +------------------------------------------------------------------ + Bra + \d*+ + \s + Ket + End +------------------------------------------------------------------ + +/\d*\S/BZ +------------------------------------------------------------------ + Bra + \d* + \S + Ket + End +------------------------------------------------------------------ + +/\d*\w/BZ +------------------------------------------------------------------ + Bra + \d* + \w + Ket + End +------------------------------------------------------------------ + +/\d*\W/BZ +------------------------------------------------------------------ + Bra + \d*+ + \W + Ket + End +------------------------------------------------------------------ + +/\D*a/BZ +------------------------------------------------------------------ + Bra + \D* + a + Ket + End +------------------------------------------------------------------ + +/\D*2/BZ +------------------------------------------------------------------ + Bra + \D*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\D*\d/BZ +------------------------------------------------------------------ + Bra + \D*+ + \d + Ket + End +------------------------------------------------------------------ + +/\D*\D/BZ +------------------------------------------------------------------ + Bra + \D* + \D + Ket + End +------------------------------------------------------------------ + +/\D*\s/BZ +------------------------------------------------------------------ + Bra + \D* + \s + Ket + End +------------------------------------------------------------------ + +/\D*\S/BZ +------------------------------------------------------------------ + Bra + \D* + \S + Ket + End +------------------------------------------------------------------ + +/\D*\w/BZ +------------------------------------------------------------------ + Bra + \D* + \w + Ket + End +------------------------------------------------------------------ + +/\D*\W/BZ +------------------------------------------------------------------ + Bra + \D* + \W + Ket + End +------------------------------------------------------------------ + +/\s*a/BZ +------------------------------------------------------------------ + Bra + \s*+ + a + Ket + End +------------------------------------------------------------------ + +/\s*2/BZ +------------------------------------------------------------------ + Bra + \s*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\s*\d/BZ +------------------------------------------------------------------ + Bra + \s*+ + \d + Ket + End +------------------------------------------------------------------ + +/\s*\D/BZ +------------------------------------------------------------------ + Bra + \s* + \D + Ket + End +------------------------------------------------------------------ + +/\s*\s/BZ +------------------------------------------------------------------ + Bra + \s* + \s + Ket + End +------------------------------------------------------------------ + +/\s*\S/BZ +------------------------------------------------------------------ + Bra + \s*+ + \S + Ket + End +------------------------------------------------------------------ + +/\s*\w/BZ +------------------------------------------------------------------ + Bra + \s*+ + \w + Ket + End +------------------------------------------------------------------ + +/\s*\W/BZ +------------------------------------------------------------------ + Bra + \s* + \W + Ket + End +------------------------------------------------------------------ + +/\S*a/BZ +------------------------------------------------------------------ + Bra + \S* + a + Ket + End +------------------------------------------------------------------ + +/\S*2/BZ +------------------------------------------------------------------ + Bra + \S* + 2 + Ket + End +------------------------------------------------------------------ + +/\S*\d/BZ +------------------------------------------------------------------ + Bra + \S* + \d + Ket + End +------------------------------------------------------------------ + +/\S*\D/BZ +------------------------------------------------------------------ + Bra + \S* + \D + Ket + End +------------------------------------------------------------------ + +/\S*\s/BZ +------------------------------------------------------------------ + Bra + \S*+ + \s + Ket + End +------------------------------------------------------------------ + +/\S*\S/BZ +------------------------------------------------------------------ + Bra + \S* + \S + Ket + End +------------------------------------------------------------------ + +/\S*\w/BZ +------------------------------------------------------------------ + Bra + \S* + \w + Ket + End +------------------------------------------------------------------ + +/\S*\W/BZ +------------------------------------------------------------------ + Bra + \S* + \W + Ket + End +------------------------------------------------------------------ + +/\w*a/BZ +------------------------------------------------------------------ + Bra + \w* + a + Ket + End +------------------------------------------------------------------ + +/\w*2/BZ +------------------------------------------------------------------ + Bra + \w* + 2 + Ket + End +------------------------------------------------------------------ + +/\w*\d/BZ +------------------------------------------------------------------ + Bra + \w* + \d + Ket + End +------------------------------------------------------------------ + +/\w*\D/BZ +------------------------------------------------------------------ + Bra + \w* + \D + Ket + End +------------------------------------------------------------------ + +/\w*\s/BZ +------------------------------------------------------------------ + Bra + \w*+ + \s + Ket + End +------------------------------------------------------------------ + +/\w*\S/BZ +------------------------------------------------------------------ + Bra + \w* + \S + Ket + End +------------------------------------------------------------------ + +/\w*\w/BZ +------------------------------------------------------------------ + Bra + \w* + \w + Ket + End +------------------------------------------------------------------ + +/\w*\W/BZ +------------------------------------------------------------------ + Bra + \w*+ + \W + Ket + End +------------------------------------------------------------------ + +/\W*a/BZ +------------------------------------------------------------------ + Bra + \W*+ + a + Ket + End +------------------------------------------------------------------ + +/\W*2/BZ +------------------------------------------------------------------ + Bra + \W*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\W*\d/BZ +------------------------------------------------------------------ + Bra + \W*+ + \d + Ket + End +------------------------------------------------------------------ + +/\W*\D/BZ +------------------------------------------------------------------ + Bra + \W* + \D + Ket + End +------------------------------------------------------------------ + +/\W*\s/BZ +------------------------------------------------------------------ + Bra + \W* + \s + Ket + End +------------------------------------------------------------------ + +/\W*\S/BZ +------------------------------------------------------------------ + Bra + \W* + \S + Ket + End +------------------------------------------------------------------ + +/\W*\w/BZ +------------------------------------------------------------------ + Bra + \W*+ + \w + Ket + End +------------------------------------------------------------------ + +/\W*\W/BZ +------------------------------------------------------------------ + Bra + \W* + \W + Ket + End +------------------------------------------------------------------ + +/[^a]+a/BZ +------------------------------------------------------------------ + Bra + [^a]++ + a + Ket + End +------------------------------------------------------------------ + +/[^a]+a/BZi +------------------------------------------------------------------ + Bra + [^A]++ + NC a + Ket + End +------------------------------------------------------------------ + +/[^a]+A/BZi +------------------------------------------------------------------ + Bra + [^A]++ + NC A + Ket + End +------------------------------------------------------------------ + +/[^a]+b/BZ +------------------------------------------------------------------ + Bra + [^a]+ + b + Ket + End +------------------------------------------------------------------ + +/[^a]+\d/BZ +------------------------------------------------------------------ + Bra + [^a]+ + \d + Ket + End +------------------------------------------------------------------ + +/a*[^a]/BZ +------------------------------------------------------------------ + Bra + a* + [^a] + Ket + End +------------------------------------------------------------------ + +/(?P<abc>x)(?P<xyz>y)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + abc 1 + xyz 2 +No options +First char = 'x' +Need char = 'y' + xy\Cabc\Cxyz + 0: xy + 1: x + 2: y + C x (1) abc + C y (1) xyz + +/(?<abc>x)(?'xyz'y)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + abc 1 + xyz 2 +No options +First char = 'x' +Need char = 'y' + xy\Cabc\Cxyz + 0: xy + 1: x + 2: y + C x (1) abc + C y (1) xyz + +/(?<abc'x)(?'xyz'y)/I +Failed: syntax error in subpattern name (missing terminator) at offset 6 + +/(?<abc>x)(?'xyz>y)/I +Failed: syntax error in subpattern name (missing terminator) at offset 15 + +/(?P'abc'x)(?P<xyz>y)/I +Failed: unrecognized character after (?P at offset 3 + +/^(?:(?(ZZ)a|b)(?<ZZ>X))+/ + bXaX + 0: bXaX + 1: X + bXbX + 0: bX + 1: X + ** Failers +No match + aXaX +No match + aXbX +No match + +/^(?P>abc)(?<abcd>xxx)/ +Failed: reference to non-existent subpattern at offset 8 + +/^(?P>abc)(?<abc>x|y)/ + xx + 0: xx + 1: x + xy + 0: xy + 1: y + yy + 0: yy + 1: y + yx + 0: yx + 1: x + +/^(?P>abc)(?P<abc>x|y)/ + xx + 0: xx + 1: x + xy + 0: xy + 1: y + yy + 0: yy + 1: y + yx + 0: yx + 1: x + +/^((?(abc)a|b)(?<abc>x|y))+/ + bxay + 0: bxay + 1: ay + 2: y + bxby + 0: bx + 1: bx + 2: x + ** Failers +No match + axby +No match + +/^(((?P=abc)|X)(?<abc>x|y))+/ + XxXxxx + 0: XxXxxx + 1: xx + 2: x + 3: x + XxXyyx + 0: XxXyyx + 1: yx + 2: y + 3: x + XxXyxx + 0: XxXy + 1: Xy + 2: X + 3: y + ** Failers +No match + x +No match + +/^(?1)(abc)/ + abcabc + 0: abcabc + 1: abc + +/^(?:(?:\1|X)(a|b))+/ + Xaaa + 0: Xaaa + 1: a + Xaba + 0: Xa + 1: a + +/^[\E\Qa\E-\Qz\E]+/BZ +------------------------------------------------------------------ + Bra + ^ + [a-z]+ + Ket + End +------------------------------------------------------------------ + +/^[a\Q]bc\E]/BZ +------------------------------------------------------------------ + Bra + ^ + [\]a-c] + Ket + End +------------------------------------------------------------------ + +/^[a-\Q\E]/BZ +------------------------------------------------------------------ + Bra + ^ + [\-a] + Ket + End +------------------------------------------------------------------ + +/^(?P>abc)[()](?<abc>)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + [()] + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^((?(abc)y)[()](?P<abc>x))+/BZ +------------------------------------------------------------------ + Bra + ^ + CBra 1 + Cond + 2 Cond ref + y + Ket + [()] + CBra 2 + x + Ket + KetRmax + Ket + End +------------------------------------------------------------------ + (xy)x + 0: (xy)x + 1: y)x + 2: x + +/^(?P>abc)\Q()\E(?<abc>)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + () + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^(?P>abc)[a\Q(]\E(](?<abc>)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + [(\]a] + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^(?P>abc) # this is (a comment) + (?<abc>)/BZx +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii +Capturing subpattern count = 4 +Max back reference = 4 +Named capturing subpatterns: + four 4 + one 1 + three 3 + two 2 +Partial matching not supported +Options: anchored caseless +No first char +No need char + 1221 + 0: 1221 + 1: 1221 + 2: 1 + Satan, oscillate my metallic sonatas! + 0: Satan, oscillate my metallic sonatas! + 1: <unset> + 2: <unset> + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: <unset> + 2: <unset> + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: <unset> + 2: <unset> + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/(?=(\w+))\1:/I +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +No options +No first char +Need char = ':' + abcd: + 0: abcd: + 1: abcd + +/(?=(?'abc'\w+))\k<abc>:/I +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + abc 1 +Partial matching not supported +No options +No first char +Need char = ':' + abcd: + 0: abcd: + 1: abcd + +/(?'abc'\w+):\k<abc>{2}/ + a:aaxyz + 0: a:aa + 1: a + ab:ababxyz + 0: ab:abab + 1: ab + ** Failers +No match + a:axyz +No match + ab:abxyz +No match + +/(?'abc'a|b)(?<abc>d|e)\k<abc>{2}/J + adaa + 0: adaa + 1: a + 2: d + ** Failers +No match + addd +No match + adbb +No match + +/(?'abc'a|b)(?<abc>d|e)(?&abc){2}/J + bdaa + 0: bdaa + 1: b + 2: d + bdab + 0: bdab + 1: b + 2: d + ** Failers +No match + bddd +No match + +/^(?<ab>a)? (?(<ab>)b|c) (?('ab')d|e)/x + abd + 0: abd + 1: a + ce + 0: ce + +/(?(<bc))/ +Failed: malformed number or name after (?( at offset 6 + +/(?(''))/ +Failed: assertion expected after (?( at offset 4 + +/(?('R')stuff)/ +Failed: reference to non-existent subpattern at offset 7 + +/((abc (?(R) (?(R1)1) (?(R2)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + 0: abcabc1Xabc2XabcX + 1: abcabc1Xabc2XabcX + 2: abcabc1Xabc2XabcX + +/(?<A> (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + 0: abcabc1Xabc2XabcX + 1: abcabc1Xabc2XabcX + 2: abcabc1Xabc2XabcX + +/(?<A> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x +Failed: reference to non-existent subpattern at offset 29 + +/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + 0: abcabc1Xabc2XabcX + 1: abcabc1Xabc2XabcX + 2: abcabc1Xabc2XabcX + +/^(?(DEFINE) (?<A> a) (?<B> b) ) (?&A) (?&B) /x + abcd + 0: ab + 1: <unset> + 2: <unset> + +/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT)) + (?(DEFINE) + (?<NAME_PAT>[a-z]+) + (?<ADDRESS_PAT>\d+) + )/x + metcalfe 33 + 0: metcalfe 33 + 1: metcalfe + 2: 33 + 3: <unset> + 4: <unset> + +/^(?(DEFINE) abc | xyz ) /x +Failed: DEFINE group contains more than one branch at offset 22 + +/(?(DEFINE) abc) xyz/xI +Capturing subpattern count = 0 +Options: extended +First char = 'x' +Need char = 'z' + +/(?(DEFINE) abc){3} xyz/x +Failed: repeating a DEFINE group is not allowed at offset 17 + +/(a|)*\d/ + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 +Matched, but too many substrings + +/^a.b/<lf> + a\rb + 0: a\x0db + a\nb\<cr> + 0: a\x0ab + a\x85b\<anycrlf> + 0: a\x85b + ** Failers +No match + a\nb +No match + a\nb\<any> +No match + a\rb\<cr> +No match + a\rb\<any> +No match + a\x85b\<any> +No match + a\rb\<anycrlf> +No match + +/^abc./mgx<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + +/abc.$/mgx<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc9 + +/a/<cr><any> + +/a/<any><crlf> +Failed: inconsistent NEWLINE options at offset 0 + +/^a\Rb/<bsr_unicode> + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/<bsr_unicode> + ab + 0: ab + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + +/^a\R+b/<bsr_unicode> + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + ** Failers +No match + ab +No match + +/^a\R{1,3}b/<bsr_unicode> + a\nb + 0: a\x0ab + a\n\rb + 0: a\x0a\x0db + a\n\r\x85b + 0: a\x0a\x0d\x85b + a\r\n\r\nb + 0: a\x0d\x0a\x0d\x0ab + a\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0ab + a\n\r\n\rb + 0: a\x0a\x0d\x0a\x0db + a\n\n\r\nb + 0: a\x0a\x0a\x0d\x0ab + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/^a[\R]b/<bsr_unicode> + aRb + 0: aRb + ** Failers +No match + a\nb +No match + +/(?&abc)X(?<abc>P)/I +Capturing subpattern count = 1 +Named capturing subpatterns: + abc 1 +No options +No first char +Need char = 'P' + abcPXP123 + 0: PXP + 1: P + +/(?1)X(?<abc>P)/I +Capturing subpattern count = 1 +Named capturing subpatterns: + abc 1 +No options +No first char +Need char = 'P' + abcPXP123 + 0: PXP + 1: P + +/(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ + 1.2.3.4 + 0: 1.2.3.4 + 1: <unset> + 2: .4 + 131.111.10.206 + 0: 131.111.10.206 + 1: <unset> + 2: .206 + 10.0.0.0 + 0: 10.0.0.0 + 1: <unset> + 2: .0 + ** Failers +No match + 10.6 +No match + 455.3.4.5 +No match + +/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ + 1.2.3.4 + 0: 1.2.3.4 + 1: .4 + 2: <unset> + 131.111.10.206 + 0: 131.111.10.206 + 1: .206 + 2: <unset> + 10.0.0.0 + 0: 10.0.0.0 + 1: .0 + 2: <unset> + ** Failers +No match + 10.6 +No match + 455.3.4.5 +No match + +/(?:a(?&abc)b)*(?<abc>x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + 123axbaxbaxb456 + 0: x + 1: x + +/(?:a(?&abc)b){1,5}(?<abc>x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(?:a(?&abc)b){2,5}(?<abc>x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(?:a(?&abc)b){2,}(?<abc>x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(abc)(?i:(?1))/ + defabcabcxyz + 0: abcabc + 1: abc + DEFabcABCXYZ +No match + +/(abc)(?:(?i)(?1))/ + defabcabcxyz + 0: abcabc + 1: abc + DEFabcABCXYZ +No match + +/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ + ababababbbabZXXXX + 0: ababababbbabZ + 1: ab + 2: b + +/^(a)\g-2/ +Failed: reference to non-existent subpattern at offset 7 + +/^(a)\g/ +Failed: a numbered reference must not be zero at offset 5 + +/^(a)\g{0}/ +Failed: a numbered reference must not be zero at offset 8 + +/^(a)\g{3/ +Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 8 + +/^(a)\g{4a}/ +Failed: reference to non-existent subpattern at offset 9 + +/^a.b/<lf> + a\rb + 0: a\x0db + *** Failers +No match + a\nb +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \r\nfoo +No match + \nfoo +No match + +/.+foo/<crlf> + afoo + 0: afoo + \nfoo + 0: \x0afoo + ** Failers +No match + \r\nfoo +No match + +/.+foo/<any> + afoo + 0: afoo + ** Failers +No match + \nfoo +No match + \r\nfoo +No match + +/.+foo/s + afoo + 0: afoo + \r\nfoo + 0: \x0d\x0afoo + \nfoo + 0: \x0afoo + +/^$/mg<any> + abc\r\rxyz + 0: + abc\n\rxyz + 0: + ** Failers +No match + abc\r\nxyz +No match + +/(?m)^$/<any>g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + +/(?m)^$|^\r\n/<any>g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + 0: \x0d\x0a + 0+ + +/(?m)$/<any>g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a\x0d\x0a + 0: + 0+ \x0d\x0a + 0: + 0+ + +/abc.$/mgx<anycrlf> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + 0: abc1 + 0: abc4 + 0: abc5 + 0: abc9 + +/^X/m + XABC + 0: X + ** Failers +No match + XABC\B +No match + +/(ab|c)(?-1)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + ab + Alt + c + Ket + Once + Recurse + Ket + Ket + End +------------------------------------------------------------------ + abc + 0: abc + 1: ab + +/xy(?+1)(abc)/BZ +------------------------------------------------------------------ + Bra + xy + Once + Recurse + Ket + CBra 1 + abc + Ket + Ket + End +------------------------------------------------------------------ + xyabcabc + 0: xyabcabc + 1: abc + ** Failers +No match + xyabc +No match + +/x(?-0)y/ +Failed: a numbered reference must not be zero at offset 5 + +/x(?-1)y/ +Failed: reference to non-existent subpattern at offset 5 + +/x(?+0)y/ +Failed: a numbered reference must not be zero at offset 5 + +/x(?+1)y/ +Failed: reference to non-existent subpattern at offset 5 + +/^(abc)?(?(-1)X|Y)/BZ +------------------------------------------------------------------ + Bra + ^ + Brazero + CBra 1 + abc + Ket + Cond + 1 Cond ref + X + Alt + Y + Ket + Ket + End +------------------------------------------------------------------ + abcX + 0: abcX + 1: abc + Y + 0: Y + ** Failers +No match + abcY +No match + +/^((?(+1)X|Y)(abc))+/BZ +------------------------------------------------------------------ + Bra + ^ + CBra 1 + Cond + 2 Cond ref + X + Alt + Y + Ket + CBra 2 + abc + Ket + KetRmax + Ket + End +------------------------------------------------------------------ + YabcXabc + 0: YabcXabc + 1: Xabc + 2: abc + YabcXabcXabc + 0: YabcXabcXabc + 1: Xabc + 2: abc + ** Failers +No match + XabcXabc +No match + +/(?(-1)a)/BZ +Failed: reference to non-existent subpattern at offset 6 + +/((?(-1)a))/BZ +------------------------------------------------------------------ + Bra + CBra 1 + Cond + 1 Cond ref + a + Ket + Ket + Ket + End +------------------------------------------------------------------ + +/((?(-2)a))/BZ +Failed: reference to non-existent subpattern at offset 7 + +/^(?(+1)X|Y)(.)/BZ +------------------------------------------------------------------ + Bra + ^ + Cond + 1 Cond ref + X + Alt + Y + Ket + CBra 1 + Any + Ket + Ket + End +------------------------------------------------------------------ + Y! + 0: Y! + 1: ! + +/(foo)\Kbar/ + foobar + 0: bar + 1: foo + +/(foo)(\Kbar|baz)/ + foobar + 0: bar + 1: foo + 2: bar + foobaz + 0: foobaz + 1: foo + 2: baz + +/(foo\Kbar)baz/ + foobarbaz + 0: barbaz + 1: foobar + +/(?<A>tom|bon)-\k{A}/ + tom-tom + 0: tom-tom + 1: tom + bon-bon + 0: bon-bon + 1: bon + ** Failers +No match + tom-bon +No match + +/(?<A>tom|bon)-\g{A}/ + tom-tom + 0: tom-tom + 1: tom + bon-bon + 0: bon-bon + 1: bon + +/\g{A/ +Failed: syntax error in subpattern name (missing terminator) at offset 4 + +/(?|(abc)|(xyz))/BZ +------------------------------------------------------------------ + Bra + Bra + CBra 1 + abc + Ket + Alt + CBra 1 + xyz + Ket + Ket + Ket + End +------------------------------------------------------------------ + >abc< + 0: abc + 1: abc + >xyz< + 0: xyz + 1: xyz + +/(x)(?|(abc)|(xyz))(x)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + x + Ket + Bra + CBra 2 + abc + Ket + Alt + CBra 2 + xyz + Ket + Ket + CBra 3 + x + Ket + Ket + End +------------------------------------------------------------------ + xabcx + 0: xabcx + 1: x + 2: abc + 3: x + xxyzx + 0: xxyzx + 1: x + 2: xyz + 3: x + +/(x)(?|(abc)(pqr)|(xyz))(x)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + x + Ket + Bra + CBra 2 + abc + Ket + CBra 3 + pqr + Ket + Alt + CBra 2 + xyz + Ket + Ket + CBra 4 + x + Ket + Ket + End +------------------------------------------------------------------ + xabcpqrx + 0: xabcpqrx + 1: x + 2: abc + 3: pqr + 4: x + xxyzx + 0: xxyzx + 1: x + 2: xyz + 3: <unset> + 4: x + +/(?|(abc)|(xyz))\1/ + abcabc + 0: abcabc + 1: abc + xyzxyz + 0: xyzxyz + 1: xyz + ** Failers +No match + abcxyz +No match + xyzabc +No match + +/(?|(abc)|(xyz))(?1)/ + abcabc + 0: abcabc + 1: abc + xyzabc + 0: xyzabc + 1: xyz + ** Failers +No match + xyzxyz +No match + +/\H\h\V\v/ + X X\x0a + 0: X X\x0a + X\x09X\x0b + 0: X\x09X\x0b + ** Failers +No match + \xa0 X\x0a +No match + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0X\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c + 0: \x09 \xa0\x0a\x0b\x0c + ** Failers +No match + \x09\x20\xa0\x0a\x0b +No match + +/\H{3,4}/ + XY ABCDE + 0: ABCD + XY PQR ST + 0: PQR + +/.\h{3,4}./ + XY AB PQRS + 0: B P + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + 0: XNNNYZ + > X NYQZ + 0: X NYQZ + ** Failers +No match + >XYZ +No match + > X NY Z +No match + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + 0: XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/[\h]/BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0] + Ket + End +------------------------------------------------------------------ + >\x09< + 0: \x09 + +/[\h]+/BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0]+ + Ket + End +------------------------------------------------------------------ + >\x09\x20\xa0< + 0: \x09 \xa0 + +/[\v]/BZ +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85] + Ket + End +------------------------------------------------------------------ + +/[\H]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] + Ket + End +------------------------------------------------------------------ + +/[^\h]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] (neg) + Ket + End +------------------------------------------------------------------ + +/[\V]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff] + Ket + End +------------------------------------------------------------------ + +/[\x0a\V]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x0a\x0e-\x84\x86-\xff] + Ket + End +------------------------------------------------------------------ + +/\H++X/BZ +------------------------------------------------------------------ + Bra + \H++ + X + Ket + End +------------------------------------------------------------------ + ** Failers +No match + XXXX +No match + +/\H+\hY/BZ +------------------------------------------------------------------ + Bra + \H++ + \h + Y + Ket + End +------------------------------------------------------------------ + XXXX Y + 0: XXXX Y + +/\H+ Y/BZ +------------------------------------------------------------------ + Bra + \H++ + Y + Ket + End +------------------------------------------------------------------ + +/\h+A/BZ +------------------------------------------------------------------ + Bra + \h++ + A + Ket + End +------------------------------------------------------------------ + +/\v*B/BZ +------------------------------------------------------------------ + Bra + \v*+ + B + Ket + End +------------------------------------------------------------------ + +/\V+\x0a/BZ +------------------------------------------------------------------ + Bra + \V++ + \x0a + Ket + End +------------------------------------------------------------------ + +/A+\h/BZ +------------------------------------------------------------------ + Bra + A++ + \h + Ket + End +------------------------------------------------------------------ + +/ *\H/BZ +------------------------------------------------------------------ + Bra + *+ + \H + Ket + End +------------------------------------------------------------------ + +/A*\v/BZ +------------------------------------------------------------------ + Bra + A*+ + \v + Ket + End +------------------------------------------------------------------ + +/\x0b*\V/BZ +------------------------------------------------------------------ + Bra + \x0b*+ + \V + Ket + End +------------------------------------------------------------------ + +/\d+\h/BZ +------------------------------------------------------------------ + Bra + \d++ + \h + Ket + End +------------------------------------------------------------------ + +/\d*\v/BZ +------------------------------------------------------------------ + Bra + \d*+ + \v + Ket + End +------------------------------------------------------------------ + +/S+\h\S+\v/BZ +------------------------------------------------------------------ + Bra + S++ + \h + \S++ + \v + Ket + End +------------------------------------------------------------------ + +/\w{3,}\h\w+\v/BZ +------------------------------------------------------------------ + Bra + \w{3} + \w*+ + \h + \w++ + \v + Ket + End +------------------------------------------------------------------ + +/\h+\d\h+\w\h+\S\h+\H/BZ +------------------------------------------------------------------ + Bra + \h++ + \d + \h++ + \w + \h++ + \S + \h++ + \H + Ket + End +------------------------------------------------------------------ + +/\v+\d\v+\w\v+\S\v+\V/BZ +------------------------------------------------------------------ + Bra + \v++ + \d + \v++ + \w + \v+ + \S + \v++ + \V + Ket + End +------------------------------------------------------------------ + +/\H+\h\H+\d/BZ +------------------------------------------------------------------ + Bra + \H++ + \h + \H+ + \d + Ket + End +------------------------------------------------------------------ + +/\V+\v\V+\w/BZ +------------------------------------------------------------------ + Bra + \V++ + \v + \V+ + \w + Ket + End +------------------------------------------------------------------ + +/\( (?: [^()]* | (?R) )* \)/x +(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + 0: (0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + +/[\E]AAA/ +Failed: missing terminating ] for character class at offset 7 + +/[\Q\E]AAA/ +Failed: missing terminating ] for character class at offset 9 + +/[^\E]AAA/ +Failed: missing terminating ] for character class at offset 8 + +/[^\Q\E]AAA/ +Failed: missing terminating ] for character class at offset 10 + +/[\E^]AAA/ +Failed: missing terminating ] for character class at offset 8 + +/[\Q\E^]AAA/ +Failed: missing terminating ] for character class at offset 10 + +/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ +------------------------------------------------------------------ + Bra + A + *PRUNE + B + *SKIP + C + *THEN + D + *COMMIT + E + *FAIL + F + *FAIL + G + *FAIL + H + *ACCEPT + I + Ket + End +------------------------------------------------------------------ + +/^a+(*FAIL)/ + aaaaaa +No match + +/a+b?c+(*FAIL)/ + aaabccc +No match + +/a+b?(*PRUNE)c+(*FAIL)/ + aaabccc +No match + +/a+b?(*COMMIT)c+(*FAIL)/ + aaabccc +No match + +/a+b?(*SKIP)c+(*FAIL)/ + aaabcccaaabccc +No match + +/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + 0: aaaxxxxxx + aaa++++++ + 0: aaa + bbbxxxxx + 0: bbbxxxxx + bbb+++++ + 0: bbb + cccxxxx + 0: cccxxxx + ccc++++ + 0: ccc + dddddddd + 0: ddd + +/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + 0: aaaxxxxxx + 1: aaaxxxxxx + aaa++++++ + 0: aaa + 1: aaa + bbbxxxxx + 0: bbbxxxxx + 1: bbbxxxxx + bbb+++++ + 0: bbb + 1: bbb + cccxxxx + 0: cccxxxx + 1: cccxxxx + ccc++++ + 0: ccc + 1: ccc + dddddddd + 0: ddd + 1: ddd + +/a+b?(*THEN)c+(*FAIL)/ + aaabccc +No match + +/(A (A|B(*ACCEPT)|C) D)(E)/x + ABX + 0: AB + AADE + 0: AADE + 1: AAD + 2: A + 3: E + ACDE + 0: ACDE + 1: ACD + 2: C + 3: E + ** Failers +No match + AD +No match + +/^a+(*FAIL)/C + aaaaaa +--->aaaaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^^ (*FAIL) +No match + +/a+b?c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^ ^ c+ + +2 ^ ^ b? + +4 ^ ^ c+ + +2 ^^ b? + +4 ^^ c+ + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^ ^ c+ + +2 ^^ b? + +4 ^^ c+ + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^^ c+ +No match + +/a+b?(*PRUNE)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) +No match + +/a+b?(*COMMIT)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*COMMIT) ++13 ^ ^ c+ ++15 ^ ^ (*FAIL) ++15 ^ ^ (*FAIL) ++15 ^ ^ (*FAIL) +No match + +/a+b?(*SKIP)c+(*FAIL)/C + aaabcccaaabccc +--->aaabcccaaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*SKIP) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*SKIP) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) +No match + +/a+b?(*THEN)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) +No match + +/a(*PRUNE:XXX)b/ +Failed: (*VERB) with an argument is not supported at offset 8 + +/a(*MARK)b/ +Failed: (*VERB) not recognized at offset 7 + +/(?i:A{1,}\6666666666)/ +Failed: number is too big at offset 19 + +/\g6666666666/ +Failed: number is too big at offset 11 + +/[\g6666666666]/ +Failed: number is too big at offset 12 + +/(?1)\c[/ +Failed: reference to non-existent subpattern at offset 3 + +/.+A/<crlf> + \r\nA +No match + +/\nA/<crlf> + \r\nA + 0: \x0aA + +/[\r\n]A/<crlf> + \r\nA + 0: \x0aA + +/(\r|\n)A/<crlf> + \r\nA + 0: \x0aA + 1: \x0a + +/a(*CR)b/ +Failed: (*VERB) not recognized at offset 5 + +/(*CR)a.b/ + a\nb + 0: a\x0ab + ** Failers +No match + a\rb +No match + +/(*CR)a.b/<lf> + a\nb + 0: a\x0ab + ** Failers +No match + a\rb +No match + +/(*LF)a.b/<CRLF> + a\rb + 0: a\x0db + ** Failers +No match + a\nb +No match + +/(*CRLF)a.b/ + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + ** Failers +No match + a\r\nb +No match + +/(*ANYCRLF)a.b/<CR> + ** Failers +No match + a\rb +No match + a\nb +No match + a\r\nb +No match + +/(*ANY)a.b/<cr> + ** Failers +No match + a\rb +No match + a\nb +No match + a\r\nb +No match + a\x85b +No match + +/a\Rb/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R{2,4}b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I<bsr_unicode> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\<bsr_anycrlf> +No match + a\x0b\0bb\<bsr_anycrlf> +No match + +/(*BSR_ANYCRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*CRLF)(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CR +First char = 'a' +Need char = 'b' + +/(?<a>)(?&)/ +Failed: subpattern name expected at offset 9 + +/(?<abc>)(?&a)/ +Failed: reference to non-existent subpattern at offset 12 + +/(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ +Failed: reference to non-existent subpattern at offset 32 + +/(?+-a)/ +Failed: digit expected after (?+ at offset 3 + +/(?-+a)/ +Failed: unrecognized character after (? or (?- at offset 3 + +/(?(-1))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+10))/ +Failed: reference to non-existent subpattern at offset 7 + +/(?(10))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ +Failed: subpattern name expected at offset 3 + +/\k<>/ +Failed: subpattern name expected at offset 3 + +/\k{}/ +Failed: subpattern name expected at offset 3 + +/(?P=)/ +Failed: subpattern name expected at offset 4 + +/(?P>)/ +Failed: subpattern name expected at offset 4 + +/(?!\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(?=\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(?<!\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 10 + +/(?<=\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 10 + +/[[:foo:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:1234:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:f\oo:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[: :]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:...:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:l\ower:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:abc\:]]/ +Failed: unknown POSIX class name at offset 3 + +/[abc[:x\]pqr:]]/ +Failed: unknown POSIX class name at offset 6 + +/[[:a\dz:]]/ +Failed: unknown POSIX class name at offset 3 + +/^(?<name>a|b\g<name>c)/ + aaaa + 0: a + 1: a + bacxxx + 0: bac + 1: bac + bbaccxxx + 0: bbacc + 1: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + +/^(?<name>a|b\g'name'c)/ + aaaa + 0: a + 1: a + bacxxx + 0: bac + 1: bac + bbaccxxx + 0: bbacc + 1: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + +/^(a|b\g<1>c)/ + aaaa + 0: a + 1: a + bacxxx + 0: bac + 1: bac + bbaccxxx + 0: bbacc + 1: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + +/^(a|b\g'1'c)/ + aaaa + 0: a + 1: a + bacxxx + 0: bac + 1: bac + bbaccxxx + 0: bbacc + 1: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + +/^(a|b\g'-1'c)/ + aaaa + 0: a + 1: a + bacxxx + 0: bac + 1: bac + bbaccxxx + 0: bbacc + 1: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + +/(^(a|b\g<-1>c))/ + aaaa + 0: a + 1: a + 2: a + bacxxx + 0: bac + 1: bac + 2: bac + bbaccxxx + 0: bbacc + 1: bbacc + 2: bbacc + bbbacccxx + 0: bbbaccc + 1: bbbaccc + 2: bbbaccc + +/(^(a|b\g<-1'c))/ +Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 15 + +/(^(a|b\g{-1}))/ + bacxxx +No match + +/(?-i:\g<name>)(?i:(?<name>a))/ + XaaX + 0: aa + 1: a + XAAX + 0: AA + 1: A + +/(?i:\g<name>)(?-i:(?<name>a))/ + XaaX + 0: aa + 1: a + ** Failers +No match + XAAX +No match + +/(?-i:\g<+1>)(?i:(a))/ + XaaX + 0: aa + 1: a + XAAX + 0: AA + 1: A + +/(?=(?<regex>(?#simplesyntax)\$(?<name>[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?<index>[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g<name>)\]|->\g<name>(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g<name>(?<indices>\[(?:\g<index>|'(?:\\.|[^'\\])*'|"(?:\g<regex>|\\.|[^"\\])*")\])?|\g<complex>|\$\{\g<complex>\})\}|(?#complexsyntax)\{(?<complex>\$(?<segment>\g<name>(\g<indices>*|\(.*?\))?)(?:->\g<segment>)*|\$\g<complex>|\$\{\g<complex>\})\}))\{/ + +/(?<n>a|b|c)\g<n>*/ + abc + 0: abc + 1: a + accccbbb + 0: accccbbb + 1: a + +/^(?+1)(?<a>x|y){0}z/ + xzxx + 0: xz + 1: <unset> + yzyy + 0: yz + 1: <unset> + ** Failers +No match + xxz +No match + +/(\3)(\1)(a)/ + cat +No match + +/(\3)(\1)(a)/<JS> + cat + 0: a + 1: + 2: + 3: a + +/TA]/ + The ACTA] comes + 0: TA] + +/TA]/<JS> +Failed: ] is an invalid data character in JavaScript compatibility mode at offset 2 + +/(?2)[]a()b](abc)/ +Failed: reference to non-existent subpattern at offset 3 + +/(?2)[^]a()b](abc)/ +Failed: reference to non-existent subpattern at offset 3 + +/(?1)[]a()b](abc)/ + abcbabc + 0: abcbabc + 1: abc + ** Failers +No match + abcXabc +No match + +/(?1)[^]a()b](abc)/ + abcXabc + 0: abcXabc + 1: abc + ** Failers +No match + abcbabc +No match + +/(?2)[]a()b](abc)(xyz)/ + xyzbabcxyz + 0: xyzbabcxyz + 1: abc + 2: xyz + +/(?&N)[]a(?<N>)](?<M>abc)/ +Failed: reference to non-existent subpattern at offset 4 + +/(?&N)[]a(?<N>)](abc)/ +Failed: reference to non-existent subpattern at offset 4 + +/a[]b/ +Failed: missing terminating ] for character class at offset 4 + +/a[^]b/ +Failed: missing terminating ] for character class at offset 5 + +/a[]b/<JS> + ** Failers +No match + ab +No match + +/a[]+b/<JS> + ** Failers +No match + ab +No match + +/a[]*+b/<JS> + ** Failers +No match + ab +No match + +/a[^]b/<JS> + aXb + 0: aXb + a\nb + 0: a\x0ab + ** Failers +No match + ab +No match + +/a[^]+b/<JS> + aXb + 0: aXb + a\nX\nXb + 0: a\x0aX\x0aXb + ** Failers +No match + ab +No match + +/a(?!)+b/ +Failed: nothing to repeat at offset 5 + +/a(*FAIL)+b/ +Failed: nothing to repeat at offset 8 + +/(abc|pqr|123){0}[xyz]/SI +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: x y z + +/(?(?=.*b)b|^)/CI +Capturing subpattern count = 0 +Partial matching not supported +Options: +No first char +No need char + adc +--->adc + +0 ^ (?(?=.*b)b|^) + +2 ^ (?=.*b) + +5 ^ .* + +7 ^ ^ b + +7 ^ ^ b + +7 ^^ b + +7 ^ b ++12 ^ ) ++13 ^ + 0: + abc +--->abc + +0 ^ (?(?=.*b)b|^) + +2 ^ (?=.*b) + +5 ^ .* + +7 ^ ^ b + +7 ^ ^ b + +7 ^^ b + +8 ^ ^ ) + +9 ^ b + +0 ^ (?(?=.*b)b|^) + +2 ^ (?=.*b) + +5 ^ .* + +7 ^ ^ b + +7 ^^ b + +7 ^ b + +8 ^^ ) + +9 ^ b ++10 ^^ | ++13 ^^ + 0: b + +/(?(?=b).*b|^d)/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/(?(?=.*b).*b|^d)/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/a?|b?/P + abc + 0: a + ** Failers + 0: + ddd\N +No match: POSIX code 17: match failed + +/xyz/C + xyz +--->xyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz +--->abcxyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz\Y +--->abcxyz + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + ** Failers +No match + abc +No match + abc\Y +--->abc + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + abcxypqr +No match + abcxypqr\Y +--->abcxypqr + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + +/^"((?(?=[a])[^"])|b)*"$/C + "ab" +--->"ab" + +0 ^ ^ + +1 ^ " + +2 ^^ ((?(?=[a])[^"])|b)* + +3 ^^ (?(?=[a])[^"]) + +5 ^^ (?=[a]) + +8 ^^ [a] ++11 ^ ^ ) ++12 ^^ [^"] ++16 ^ ^ ) ++17 ^ ^ | + +3 ^ ^ (?(?=[a])[^"]) + +5 ^ ^ (?=[a]) + +8 ^ ^ [a] ++21 ^ ^ " ++18 ^ ^ b ++19 ^ ^ ) + +3 ^ ^ (?(?=[a])[^"]) + +5 ^ ^ (?=[a]) + +8 ^ ^ [a] ++21 ^ ^ " ++22 ^ ^ $ ++23 ^ ^ + 0: "ab" + 1: + +/^"((?(?=[a])[^"])|b)*"$/ + "ab" + 0: "ab" + 1: + +/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/ + XYabcdY + 0: XYabcdY + 1: a + 2: b + 3: c + 4: d + 5: Y + +/^X(?5)(a)(?|(b)|(q))(c)(d)Y/ +Failed: reference to non-existent subpattern at offset 5 + +/^X(?&N)(a)(?|(b)|(q))(c)(d)(?<N>Y)/ + XYabcdY + 0: XYabcdY + 1: a + 2: b + 3: c + 4: d + 5: Y + +/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/ + XYabcdY + 0: XYabcdY + 1: a + 2: b + 3: <unset> + 4: <unset> + 5: c + 6: d + 7: Y + +/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/ + XYabcdY + 0: XYabcdY + 1: a + 2: b + 3: <unset> + 4: <unset> + 5: c + 6: d + 7: Y + +/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/ + XYabcdY + 0: XYabcdY + 1: a + 2: b + 3: <unset> + 4: <unset> + 5: c + 6: d + 7: Y + +/ End of testinput2 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput3 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput3 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput3 Mon Jun 8 18:51:30 2009 @@ -146,14 +146,14 @@ >>>\xba<<< 0: � -/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR ------------------------------------------------------------------ - 0 102 Bra 0 - 3 [A-Za-z����-��-��-�] - 36 [a-z��-��-�] - 69 [A-Z�-��-�] -102 102 Ket -105 End + Bra + [A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] + [a-z\xb5\xdf-\xf6\xf8-\xff] + [A-Z\xc0-\xd6\xd8-\xde] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options Modified: freeswitch/trunk/libs/pcre/testdata/testoutput4 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput4 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput4 Mon Jun 8 18:51:30 2009 @@ -914,4 +914,179 @@ 0: ab 1: ab +/a*\x{100}*\w/8 + a + 0: a + +/\S\S/8g + A\x{a3}BC + 0: A\x{a3} + 0: BC + +/\S{2}/8g + A\x{a3}BC + 0: A\x{a3} + 0: BC + +/\W\W/8g + +\x{a3}== + 0: +\x{a3} + 0: == + +/\W{2}/8g + +\x{a3}== + 0: +\x{a3} + 0: == + +/\S/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/[\S]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/\D/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/[\D]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/\W/8g + \x{2442}\x{2435}\x{2441}\x{2442} + 0: \x{2442} + 0: \x{2435} + 0: \x{2441} + 0: \x{2442} + +/[\W]/8g + \x{2442}\x{2435}\x{2441}\x{2442} + 0: \x{2442} + 0: \x{2435} + 0: \x{2441} + 0: \x{2442} + +/[\S\s]*/8 + abc\n\r\x{442}\x{435}\x{441}\x{442}xyz + 0: abc\x{0a}\x{0d}\x{442}\x{435}\x{441}\x{442}xyz + +/[\x{41f}\S]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/.[^\S]./8g + abc def\x{442}\x{443}xyz\npqr + 0: c d + 0: z\x{0a}p + +/.[^\S\n]./8g + abc def\x{442}\x{443}xyz\npqr + 0: c d + +/[[:^alnum:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^alpha:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^ascii:]]/8g + A\x{442} + 0: \x{442} + +/[[:^blank:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^cntrl:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^digit:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^graph:]]/8g + \x19\x{e01ff} + 0: \x{19} + 0: \x{e01ff} + +/[[:^lower:]]/8g + A\x{422} + 0: A + 0: \x{422} + +/[[:^print:]]/8g + \x{19}\x{e01ff} + 0: \x{19} + 0: \x{e01ff} + +/[[:^punct:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^space:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^upper:]]/8g + a\x{442} + 0: a + 0: \x{442} + +/[[:^word:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^xdigit:]]/8g + M\x{442} + 0: M + 0: \x{442} + +/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉƊƋƎƏƐƑƓƔƖƗƘƜƝƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀʁʂʃʄʅʆʇʈʉʊʋʌʍʎʏʐʑʒʓʔʕʖʗʘʙʚʛʜʝʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯΐάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώϐϑϕϖϗϙϛϝϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹԁԃԅԇԉԋԍԏաբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆևᴀᴁᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌᴍᴎᴏᴐᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜᴝᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀᶁᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌᶍᶎᶏᶐᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇῐῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣⳤⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥfffiflffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 + +/^[^d]*?$/ + abc + 0: abc + +/^[^d]*?$/8 + abc + 0: abc + +/^[^d]*?$/i + abc + 0: abc + +/^[^d]*?$/8i + abc + 0: abc + +/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8 + / End of testinput4 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput5 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput5 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput5 Mon Jun 8 18:51:30 2009 @@ -1,114 +1,105 @@ -/\x{100}/8DM -Memory allocation (code space): 10 +/\x{100}/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{100} - 6 6 Ket - 9 End + Bra + \x{100} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 196 Need char = 128 -/\x{1000}/8DM -Memory allocation (code space): 11 +/\x{1000}/8DZ ------------------------------------------------------------------ - 0 7 Bra 0 - 3 \x{1000} - 7 7 Ket - 10 End + Bra + \x{1000} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 225 Need char = 128 -/\x{10000}/8DM -Memory allocation (code space): 12 +/\x{10000}/8DZ ------------------------------------------------------------------ - 0 8 Bra 0 - 3 \x{10000} - 8 8 Ket - 11 End + Bra + \x{10000} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 240 Need char = 128 -/\x{100000}/8DM -Memory allocation (code space): 12 +/\x{100000}/8DZ ------------------------------------------------------------------ - 0 8 Bra 0 - 3 \x{100000} - 8 8 Ket - 11 End + Bra + \x{100000} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 244 Need char = 128 -/\x{1000000}/8DM -Memory allocation (code space): 13 +/\x{1000000}/8DZ ------------------------------------------------------------------ - 0 9 Bra 0 - 3 \x{1000000} - 9 9 Ket - 12 End + Bra + \x{1000000} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 249 Need char = 128 -/\x{4000000}/8DM -Memory allocation (code space): 14 +/\x{4000000}/8DZ ------------------------------------------------------------------ - 0 10 Bra 0 - 3 \x{4000000} - 10 10 Ket - 13 End + Bra + \x{4000000} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 252 Need char = 128 -/\x{7fffFFFF}/8DM -Memory allocation (code space): 14 +/\x{7fffFFFF}/8DZ ------------------------------------------------------------------ - 0 10 Bra 0 - 3 \x{7fffffff} - 10 10 Ket - 13 End + Bra + \x{7fffffff} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 253 Need char = 191 -/[\x{ff}]/8DM -Memory allocation (code space): 10 +/[\x{ff}]/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End + Bra + \x{ff} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 195 Need char = 191 -/[\x{100}]/8DM -Memory allocation (code space): 47 +/[\x{100}]/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End + Bra + [\x{100}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -125,36 +116,36 @@ \x{100}a\x{1234}bcd 0: \x{100}a\x{1234} -/\x80/8D +/\x80/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{80} - 6 6 Ket - 9 End + Bra + \x{80} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 194 Need char = 128 -/\xff/8D +/\xff/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End + Bra + \x{ff} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 195 Need char = 191 -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 +/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 ------------------------------------------------------------------ - 0 14 Bra 0 - 3 A\x{2262}\x{391}. - 14 14 Ket - 17 End + Bra + A\x{2262}\x{391}. + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -163,12 +154,12 @@ \x{0041}\x{2262}\x{0391}\x{002e} 0: A\x{2262}\x{391}. -/\x{D55c}\x{ad6d}\x{C5B4}/D8 +/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 ------------------------------------------------------------------ - 0 15 Bra 0 - 3 \x{d55c}\x{ad6d}\x{c5b4} - 15 15 Ket - 18 End + Bra + \x{d55c}\x{ad6d}\x{c5b4} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -177,12 +168,12 @@ \x{D55c}\x{ad6d}\x{C5B4} 0: \x{d55c}\x{ad6d}\x{c5b4} -/\x{65e5}\x{672c}\x{8a9e}/D8 +/\x{65e5}\x{672c}\x{8a9e}/DZ8 ------------------------------------------------------------------ - 0 15 Bra 0 - 3 \x{65e5}\x{672c}\x{8a9e} - 15 15 Ket - 18 End + Bra + \x{65e5}\x{672c}\x{8a9e} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -191,74 +182,74 @@ \x{65e5}\x{672c}\x{8a9e} 0: \x{65e5}\x{672c}\x{8a9e} -/\x{80}/D8 +/\x{80}/DZ8 ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{80} - 6 6 Ket - 9 End + Bra + \x{80} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 194 Need char = 128 -/\x{084}/D8 +/\x{084}/DZ8 ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{84} - 6 6 Ket - 9 End + Bra + \x{84} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 194 Need char = 132 -/\x{104}/D8 +/\x{104}/DZ8 ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{104} - 6 6 Ket - 9 End + Bra + \x{104} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 196 Need char = 132 -/\x{861}/D8 +/\x{861}/DZ8 ------------------------------------------------------------------ - 0 7 Bra 0 - 3 \x{861} - 7 7 Ket - 10 End + Bra + \x{861} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 224 Need char = 161 -/\x{212ab}/D8 +/\x{212ab}/DZ8 ------------------------------------------------------------------ - 0 8 Bra 0 - 3 \x{212ab} - 8 8 Ket - 11 End + Bra + \x{212ab} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 240 Need char = 171 -/.{3,5}X/D8 +/.{3,5}X/DZ8 ------------------------------------------------------------------ - 0 13 Bra 0 - 3 Any{3} - 7 Any{0,2} - 11 X - 13 13 Ket - 16 End + Bra + Any{3} + Any{0,2} + X + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -269,13 +260,13 @@ 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X -/.{3,5}?/D8 +/.{3,5}?/DZ8 ------------------------------------------------------------------ - 0 11 Bra 0 - 3 Any{3} - 7 Any{0,2}? - 11 11 Ket - 14 End + Bra + Any{3} + Any{0,2}? + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -285,11 +276,9 @@ \x{212ab}\x{212ab}\x{212ab}\x{861} 0: \x{212ab}\x{212ab}\x{212ab} -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -No match -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ -No match +/-- These tests are here rather than in testinput4 because Perl 5.6 has some +problems with UTF-8 support, in the area of \x{..} where the value is < 255. +It grumbles about invalid UTF-8 strings. --/ /^[a\x{c0}]b/8 \x{c0}b @@ -329,11 +318,9 @@ /(?<=\C)X/8 Failed: \C not allowed in lookbehind assertion at offset 6 -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -No match -/-- character, and you can't tell the difference.) --/ -No match +/-- This one is here not because it's different to Perl, but because the way +the captured single-byte is displayed. (In Perl it becomes a character, and you +can't tell the difference.) --/ /X(\C)(.*)/8 X\x{1234} @@ -345,13 +332,13 @@ 1: \x{0a} 2: abc -/^[ab]/8D +/^[ab]/8DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [ab] - 37 37 Ket - 40 End + Bra + ^ + [ab] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored utf8 @@ -368,13 +355,13 @@ \x{100} No match -/^[^ab]/8D +/^[^ab]/8DZ ------------------------------------------------------------------ - 0 37 Bra 0 - 3 ^ - 4 [\x00-`c-\xff] (neg) - 37 37 Ket - 40 End + Bra + ^ + [\x00-`c-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored utf8 @@ -391,12 +378,12 @@ aaa No match -/[^ab\xC0-\xF0]/8SD +/[^ab\xC0-\xF0]/8SDZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x00-`c-\xbf\xf1-\xff] (neg) - 36 36 Ket - 39 End + Bra + [\x00-`c-\xbf\xf1-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -427,13 +414,13 @@ \x{f0} No match -/Ā{3,4}/8SD +/Ā{3,4}/8SDZ ------------------------------------------------------------------ - 0 13 Bra 0 - 3 \x{100}{3} - 8 \x{100}{,1} - 13 13 Ket - 16 End + Bra + \x{100}{3} + \x{100}? + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -444,16 +431,16 @@ \x{100}\x{100}\x{100}\x{100\x{100} 0: \x{100}\x{100}\x{100} -/(\x{100}+|x)/8SD +/(\x{100}+|x)/8SDZ ------------------------------------------------------------------ - 0 17 Bra 0 - 3 6 Bra 1 - 6 \x{100}+ - 9 5 Alt - 12 x - 14 11 Ket - 17 17 Ket - 20 End + Bra + CBra 1 + \x{100}+ + Alt + x + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -462,17 +449,17 @@ No need char Starting byte set: x \xc4 -/(\x{100}*a|x)/8SD +/(\x{100}*a|x)/8SDZ ------------------------------------------------------------------ - 0 19 Bra 0 - 3 8 Bra 1 - 6 \x{100}* - 9 a - 11 5 Alt - 14 x - 16 13 Ket - 19 19 Ket - 22 End + Bra + CBra 1 + \x{100}*+ + a + Alt + x + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -481,17 +468,17 @@ No need char Starting byte set: a x \xc4 -/(\x{100}{0,2}a|x)/8SD +/(\x{100}{0,2}a|x)/8SDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 10 Bra 1 - 6 \x{100}{,2} - 11 a - 13 5 Alt - 16 x - 18 15 Ket - 21 21 Ket - 24 End + Bra + CBra 1 + \x{100}{0,2} + a + Alt + x + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -500,18 +487,18 @@ No need char Starting byte set: a x \xc4 -/(\x{100}{1,2}a|x)/8SD +/(\x{100}{1,2}a|x)/8SDZ ------------------------------------------------------------------ - 0 24 Bra 0 - 3 13 Bra 1 - 6 \x{100} - 9 \x{100}{,1} - 14 a - 16 5 Alt - 19 x - 21 18 Ket - 24 24 Ket - 27 End + Bra + CBra 1 + \x{100} + \x{100}{0,1} + a + Alt + x + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Partial matching not supported @@ -544,24 +531,24 @@ \x{100}\x{100}abcd No match -/\x{100}/8D +/\x{100}/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{100} - 6 6 Ket - 9 End + Bra + \x{100} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 196 Need char = 128 -/\x{100}*/8D +/\x{100}*/8DZ ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{100}* - 6 6 Ket - 9 End + Bra + \x{100}* + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -569,13 +556,13 @@ No first char No need char -/a\x{100}*/8D +/a\x{100}*/8DZ ------------------------------------------------------------------ - 0 8 Bra 0 - 3 a - 5 \x{100}* - 8 8 Ket - 11 End + Bra + a + \x{100}* + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -583,13 +570,13 @@ First char = 'a' No need char -/ab\x{100}*/8D +/ab\x{100}*/8DZ ------------------------------------------------------------------ - 0 10 Bra 0 - 3 ab - 7 \x{100}* - 10 10 Ket - 13 End + Bra + ab + \x{100}* + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -597,13 +584,13 @@ First char = 'a' Need char = 'b' -/a\x{100}\x{101}*/8D +/a\x{100}\x{101}*/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 a\x{100} - 8 \x{101}* - 11 11 Ket - 14 End + Bra + a\x{100} + \x{101}* + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -611,13 +598,13 @@ First char = 'a' Need char = 128 -/a\x{100}\x{101}+/8D +/a\x{100}\x{101}+/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 a\x{100} - 8 \x{101}+ - 11 11 Ket - 14 End + Bra + a\x{100} + \x{101}+ + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -625,13 +612,13 @@ First char = 'a' Need char = 129 -/\x{100}*A/8D +/\x{100}*A/8DZ ------------------------------------------------------------------ - 0 8 Bra 0 - 3 \x{100}* - 6 A - 8 8 Ket - 11 End + Bra + \x{100}*+ + A + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -641,16 +628,16 @@ A 0: A -/\x{100}*\d(?R)/8D +/\x{100}*\d(?R)/8DZ ------------------------------------------------------------------ - 0 16 Bra 0 - 3 \x{100}* - 6 \d - 7 6 Once - 10 0 Recurse - 13 6 Ket - 16 16 Ket - 19 End + Bra + \x{100}*+ + \d + Once + Recurse + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -658,37 +645,36 @@ No first char No need char -/[^\x{c4}]/D +/[^\x{c4}]/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 [^\xc4] - 5 5 Ket - 8 End + Bra + [^\xc4] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[^\x{c4}]/8D +/[^\x{c4}]/8DZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x00-\xc3\xc5-\xff] (neg) - 36 36 Ket - 39 End + Bra + [\x00-\xc3\xc5-\xff] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 No first char No need char -/[\x{100}]/8DM -Memory allocation (code space): 47 +/[\x{100}]/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End + Bra + [\x{100}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -703,13 +689,12 @@ *** Failers No match -/[Z\x{100}]/8DM -Memory allocation (code space): 47 +/[Z\x{100}]/8DZ ------------------------------------------------------------------ - 0 43 Bra 0 - 3 [Z\x{100}] - 43 43 Ket - 46 End + Bra + [Z\x{100}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -739,24 +724,24 @@ \x{ff} No match -/[z-\x{100}]/8D +/[z-\x{100}]/8DZ ------------------------------------------------------------------ - 0 12 Bra 0 - 3 [z-\x{100}] - 12 12 Ket - 15 End + Bra + [z-\x{100}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 No first char No need char -/[z\Qa-d]Ā\E]/8D +/[z\Qa-d]Ā\E]/8DZ ------------------------------------------------------------------ - 0 43 Bra 0 - 3 [\-\]adz\x{100}] - 43 43 Ket - 46 End + Bra + [\-\]adz\x{100}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -767,12 +752,12 @@ Ā 0: \x{100} -/[\xFF]/D +/[\xFF]/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 \xff - 5 5 Ket - 8 End + Bra + \xff + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options @@ -781,12 +766,12 @@ >\xff< 0: \xff -/[\xff]/D8 +/[\xff]/DZ8 ------------------------------------------------------------------ - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End + Bra + \x{ff} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -795,24 +780,24 @@ >\x{ff}< 0: \x{ff} -/[^\xFF]/D +/[^\xFF]/DZ ------------------------------------------------------------------ - 0 5 Bra 0 - 3 [^\xff] - 5 5 Ket - 8 End + Bra + [^\xff] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[^\xff]/8D +/[^\xff]/8DZ ------------------------------------------------------------------ - 0 36 Bra 0 - 3 [\x00-\xfe] (neg) - 36 36 Ket - 39 End + Bra + [\x00-\xfe] (neg) + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -852,12 +837,12 @@ /���xxx/8 Failed: invalid UTF-8 string at offset 1 -/���xxx/8?D +/���xxx/8?DZ ------------------------------------------------------------------ - 0 15 Bra 0 - 3 \X{c0}\X{c0}\X{c0}xxx - 15 15 Ket - 18 End + Bra + \X{c0}\X{c0}\X{c0}xxx + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 no_utf8_check @@ -902,178 +887,186 @@ \xf1\x8f\x80\x80 No match \xf8\x88\x80\x80\x80 -No match +Error -10 \xf9\x87\x80\x80\x80 -No match +Error -10 \xfc\x84\x80\x80\x80\x80 -No match +Error -10 \xfd\x83\x80\x80\x80\x80 +Error -10 + \?\xf8\x88\x80\x80\x80 +No match + \?\xf9\x87\x80\x80\x80 +No match + \?\xfc\x84\x80\x80\x80\x80 +No match + \?\xfd\x83\x80\x80\x80\x80 No match -/\x{100}abc(xyz(?1))/8D +/\x{100}abc(xyz(?1))/8DZ ------------------------------------------------------------------ - 0 33 Bra 0 - 3 \x{100}abc - 12 18 Bra 1 - 15 xyz - 21 6 Once - 24 12 Recurse - 27 6 Ket - 30 18 Ket - 33 33 Ket - 36 End + Bra + \x{100}abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf8 First char = 196 Need char = 'z' -/[^\x{100}]abc(xyz(?1))/8D +/[^\x{100}]abc(xyz(?1))/8DZ ------------------------------------------------------------------ - 0 38 Bra 0 - 3 [^\x{100}] - 11 abc - 17 18 Bra 1 - 20 xyz - 26 6 Once - 29 17 Recurse - 32 6 Ket - 35 18 Ket - 38 38 Ket - 41 End + Bra + [^\x{100}] + abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf8 No first char Need char = 'z' -/[ab\x{100}]abc(xyz(?1))/8D +/[ab\x{100}]abc(xyz(?1))/8DZ ------------------------------------------------------------------ - 0 70 Bra 0 - 3 [ab\x{100}] - 43 abc - 49 18 Bra 1 - 52 xyz - 58 6 Once - 61 49 Recurse - 64 6 Ket - 67 18 Ket - 70 70 Ket - 73 End + Bra + [ab\x{100}] + abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf8 No first char Need char = 'z' -/(\x{100}(b(?2)c))?/D8 +/(\x{100}(b(?2)c))?/DZ8 ------------------------------------------------------------------ - 0 32 Bra 0 - 3 Brazero - 4 25 Bra 1 - 7 \x{100} - 10 16 Bra 2 - 13 b - 15 6 Once - 18 10 Recurse - 21 6 Ket - 24 c - 26 16 Ket - 29 25 Ket - 32 32 Ket - 35 End + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Options: utf8 No first char No need char -/(\x{100}(b(?2)c)){0,2}/D8 +/(\x{100}(b(?2)c)){0,2}/DZ8 ------------------------------------------------------------------ - 0 67 Bra 0 - 3 Brazero - 4 60 Bra 0 - 7 25 Bra 1 - 10 \x{100} - 13 16 Bra 2 - 16 b - 18 6 Once - 21 13 Recurse - 24 6 Ket - 27 c - 29 16 Ket - 32 25 Ket - 35 Brazero - 36 25 Bra 1 - 39 \x{100} - 42 16 Bra 2 - 45 b - 47 6 Once - 50 13 Recurse - 53 6 Ket - 56 c - 58 16 Ket - 61 25 Ket - 64 60 Ket - 67 67 Ket - 70 End + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Options: utf8 No first char No need char -/(\x{100}(b(?1)c))?/D8 +/(\x{100}(b(?1)c))?/DZ8 ------------------------------------------------------------------ - 0 32 Bra 0 - 3 Brazero - 4 25 Bra 1 - 7 \x{100} - 10 16 Bra 2 - 13 b - 15 6 Once - 18 4 Recurse - 21 6 Ket - 24 c - 26 16 Ket - 29 25 Ket - 32 32 Ket - 35 End + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Options: utf8 No first char No need char -/(\x{100}(b(?1)c)){0,2}/D8 +/(\x{100}(b(?1)c)){0,2}/DZ8 ------------------------------------------------------------------ - 0 67 Bra 0 - 3 Brazero - 4 60 Bra 0 - 7 25 Bra 1 - 10 \x{100} - 13 16 Bra 2 - 16 b - 18 6 Once - 21 7 Recurse - 24 6 Ket - 27 c - 29 16 Ket - 32 25 Ket - 35 Brazero - 36 25 Bra 1 - 39 \x{100} - 42 16 Bra 2 - 45 b - 47 6 Once - 50 7 Recurse - 53 6 Ket - 56 c - 58 16 Ket - 61 25 Ket - 64 60 Ket - 67 67 Ket - 70 End + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 2 Options: utf8 @@ -1094,13 +1087,13 @@ a\x{1234}b 0: a\x{1234}b -/^\ሴ/8D +/^\ሴ/8DZ ------------------------------------------------------------------ - 0 8 Bra 0 - 3 ^ - 4 \x{1234} - 8 8 Ket - 11 End + Bra + ^ + \x{1234} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: anchored utf8 @@ -1119,5 +1112,544 @@ 0: \x{1ff} \777 0: \x{1ff} + +/\x{100}*\d/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\s/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \s + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\w/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \w + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\D/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \D + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\S/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \S + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\W/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \W + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}+\x{200}/8DZ +------------------------------------------------------------------ + Bra + \x{100}++ + \x{200} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 128 + +/\x{100}+X/8DZ +------------------------------------------------------------------ + Bra + \x{100}++ + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 'X' + +/X+\x{200}/8DZ +------------------------------------------------------------------ + Bra + X++ + \x{200} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'X' +Need char = 128 + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/8x + AxxB +Matched, but too many substrings + 0: AxxB + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: +11: +12: +13: +14: + +/^[\x{100}\E-\Q\E\x{150}]/BZ8 +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E]/BZ8 +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E/BZ8 +Failed: missing terminating ] for character class at offset 15 + +/^abc./mgx8<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/mgx8<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/8<bsr_unicode> + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\H\h\V\v/8 + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/[\h]/8BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}] + Ket + End +------------------------------------------------------------------ + >\x{1680} + 0: \x{1680} + +/[\h]{3,}/8BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,} + Ket + End +------------------------------------------------------------------ + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + 0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000} + +/[\v]/8BZ +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85\x{2028}-\x{2029}] + Ket + End +------------------------------------------------------------------ + +/[\H]/8BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{7fffffff}] + Ket + End +------------------------------------------------------------------ + +/[\V]/8BZ +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{2029}-\x{7fffffff}] + Ket + End +------------------------------------------------------------------ + +/.*$/8<any> + \x{1ec5} + 0: \x{1ec5} + +/-- This tests the stricter UTF-8 check according to RFC 3629. --/ + +/X/8 + \x{0}\x{d7ff}\x{e000}\x{10ffff} +No match + \x{d800} +Error -10 + \x{d800}\? +No match + \x{da00} +Error -10 + \x{da00}\? +No match + \x{dfff} +Error -10 + \x{dfff}\? +No match + \x{110000} +Error -10 + \x{110000}\? +No match + \x{2000000} +Error -10 + \x{2000000}\? +No match + \x{7fffffff} +Error -10 + \x{7fffffff}\? +No match + +/a\Rb/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/.*a.*=.b.*/8<ANY> + QQQ\x{2029}ABCaXYZ=!bPQR + 0: ABCaXYZ=!bPQR + ** Failers +No match + a\x{2029}b +No match + \x61\xe2\x80\xa9\x62 +No match + +/[[:a\x{100}b:]]/8 +Failed: unknown POSIX class name at offset 3 + +/a[^]b/<JS>8 + a\x{1234}b + 0: a\x{1234}b + a\nb + 0: a\x{0a}b + ** Failers +No match + ab +No match + +/a[^]+b/<JS>8 + aXb + 0: aXb + a\nX\nX\x{1234}b + 0: a\x{0a}X\x{0a}X\x{1234}b + ** Failers +No match + ab +No match + +/(\x{de})\1/ + \x{de}\x{de} + 0: \xde\xde + 1: \xde + \x{123} +** Character \x{123} is greater than 255 and UTF-8 mode is not enabled. +** Truncation will probably give the wrong result. +No match + +/X/8f<any> + A\x{1ec5}ABCXYZ + 0: X + +/(*UTF8)\x{1234}/ + abcd\x{1234}pqr + 0: \x{1234} + +/(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' / End of testinput5 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput6 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput6 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput6 Mon Jun 8 18:51:30 2009 @@ -99,7 +99,7 @@ No match /^\p{Cs}/8 - \x{dfff} + \?\x{dfff} 0: \x{dfff} ** Failers No match @@ -113,7 +113,7 @@ No match Z No match - \x{dfff} + \x{e000} No match /^\p{Lm}/8 @@ -548,73 +548,72 @@ WXYZ No match -/[\p{L}]/D +/[\p{L}]/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\p{L}] - 11 11 Ket - 14 End + Bra + [\p{L}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[\p{^L}]/D +/[\p{^L}]/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\P{L}] - 11 11 Ket - 14 End + Bra + [\P{L}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[\P{L}]/D +/[\P{L}]/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\P{L}] - 11 11 Ket - 14 End + Bra + [\P{L}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[\P{^L}]/D +/[\P{^L}]/DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\p{L}] - 11 11 Ket - 14 End + Bra + [\p{L}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first char No need char -/[abc\p{L}\x{0660}]/8D +/[abc\p{L}\x{0660}]/8DZ ------------------------------------------------------------------ - 0 46 Bra 0 - 3 [a-c\p{L}\x{660}] - 46 46 Ket - 49 End + Bra + [a-c\p{L}\x{660}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 No first char No need char -/[\p{Nd}]/8DM -Memory allocation (code space): 47 +/[\p{Nd}]/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 [\p{Nd}] - 11 11 Ket - 14 End + Bra + [\p{Nd}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 @@ -623,13 +622,12 @@ 1234 0: 1 -/[\p{Nd}+-]+/8DM -Memory allocation (code space): 48 +/[\p{Nd}+-]+/8DZ ------------------------------------------------------------------ - 0 44 Bra 0 - 3 [+\-\p{Nd}]+ - 44 44 Ket - 47 End + Bra + [+\-\p{Nd}]+ + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Partial matching not supported @@ -779,48 +777,48 @@ A\x{391}\x{10427}\x{ff3a}\x{1fb8} 0: A\x{391}\x{10427}\x{ff3a}\x{1fb8} -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iDZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End + Bra + NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf8 First char = 'A' (caseless) No need char -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8DZ ------------------------------------------------------------------ - 0 21 Bra 0 - 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End + Bra + A\x{391}\x{10427}\x{ff3a}\x{1fb0} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 'A' Need char = 176 -/AB\x{1fb0}/8D +/AB\x{1fb0}/8DZ ------------------------------------------------------------------ - 0 11 Bra 0 - 3 AB\x{1fb0} - 11 11 Ket - 14 End + Bra + AB\x{1fb0} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf8 First char = 'A' Need char = 176 -/AB\x{1fb0}/8Di +/AB\x{1fb0}/8DZi ------------------------------------------------------------------ - 0 11 Bra 0 - 3 NC AB\x{1fb0} - 11 11 Ket - 14 End + Bra + NC AB\x{1fb0} + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf8 @@ -857,12 +855,12 @@ \x{e0} 0: \x{e0} -/[\x{105}-\x{109}]/8iD +/[\x{105}-\x{109}]/8iDZ ------------------------------------------------------------------ - 0 13 Bra 0 - 3 [\x{104}-\x{109}] - 13 13 Ket - 16 End + Bra + [\x{104}-\x{109}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf8 @@ -881,12 +879,12 @@ \x{10a} No match -/[z-\x{100}]/8iD +/[z-\x{100}]/8iDZ ------------------------------------------------------------------ - 0 20 Bra 0 - 3 [Z\x{39c}\x{178}z-\x{101}] - 20 20 Ket - 23 End + Bra + [Z\x{39c}\x{178}z-\x{101}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf8 @@ -919,12 +917,12 @@ y No match -/[z-\x{100}]/8Di +/[z-\x{100}]/8DZi ------------------------------------------------------------------ - 0 20 Bra 0 - 3 [Z\x{39c}\x{178}z-\x{101}] - 20 20 Ket - 23 End + Bra + [Z\x{39c}\x{178}z-\x{101}] + Ket + End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf8 @@ -1410,4 +1408,353 @@ 1: L=abc 2: abc +/The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE +will match it only with UCP support, because without that it has no notion +of case for anything other than the ASCII letters. / + +/((?i)[\x{c0}])/8 + \x{c0} + 0: \x{c0} + 1: \x{c0} + \x{e0} + 0: \x{e0} + 1: \x{e0} + +/(?i:[\x{c0}])/8 + \x{c0} + 0: \x{c0} + \x{e0} + 0: \x{e0} + +/^\p{Balinese}\p{Cuneiform}\p{Nko}\p{Phags_Pa}\p{Phoenician}/8 + \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900} + 0: \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900} + +/The next two are special cases where the lengths of the different cases of the +same character differ. The first went wrong with heap frame storage; the 2nd +was broken in all cases./ + +/^\x{023a}+?(\x{0130}+)/8i + \x{023a}\x{2c65}\x{0130} + 0: \x{23a}\x{2c65}\x{130} + 1: \x{130} + +/^\x{023a}+([^X])/8i + \x{023a}\x{2c65}X + 0: \x{23a}\x{2c65} + 1: \x{2c65} + +/Check property support in non-UTF-8 mode/ + +/\p{L}{4}/ + 123abcdefg + 0: abcd + 123abc\xc4\xc5zz + 0: abc\xc4 + +/\X{1,3}\d/ + \x8aBCD +No match + +/\X?\d/ + \x8aBCD +No match + +/\P{L}?\d/ + \x8aBCD +No match + +/[\PPP\x8a]{1,}\x80/ + A\x80 + 0: A\x80 + +/(?:[\PPa*]*){8,}/ + +/[\P{Any}]/BZ +------------------------------------------------------------------ + Bra + [\P{Any}] + Ket + End +------------------------------------------------------------------ + +/[\P{Any}\E]/BZ +------------------------------------------------------------------ + Bra + [\P{Any}] + Ket + End +------------------------------------------------------------------ + +/(\P{Yi}+\277)/ + +/(\P{Yi}+\277)?/ + +/(?<=\P{Yi}{3}A)X/ + +/\p{Yi}+(\P{Yi}+)(?1)/ + +/(\P{Yi}{2}\277)?/ + +/[\P{Yi}A]/ + +/[\P{Yi}\P{Yi}\P{Yi}A]/ + +/[^\P{Yi}A]/ + +/[^\P{Yi}\P{Yi}\P{Yi}A]/ + +/(\P{Yi}*\277)*/ + +/(\P{Yi}*?\277)*/ + +/(\p{Yi}*+\277)*/ + +/(\P{Yi}?\277)*/ + +/(\P{Yi}??\277)*/ + +/(\p{Yi}?+\277)*/ + +/(\P{Yi}{0,3}\277)*/ + +/(\P{Yi}{0,3}?\277)*/ + +/(\p{Yi}{0,3}+\277)*/ + +/^[\p{Arabic}]/8 + \x{60e} + 0: \x{60e} + \x{656} + 0: \x{656} + \x{657} + 0: \x{657} + \x{658} + 0: \x{658} + \x{659} + 0: \x{659} + \x{65a} + 0: \x{65a} + \x{65b} + 0: \x{65b} + \x{65c} + 0: \x{65c} + \x{65d} + 0: \x{65d} + \x{65e} + 0: \x{65e} + \x{66a} + 0: \x{66a} + \x{6e9} + 0: \x{6e9} + \x{6ef} + 0: \x{6ef} + \x{6fa} + 0: \x{6fa} + ** Failers +No match + \x{600} +No match + \x{650} +No match + \x{651} +No match + \x{652} +No match + \x{653} +No match + \x{654} +No match + \x{655} +No match + \x{65f} +No match + +/^\p{Cyrillic}/8 + \x{1d2b} + 0: \x{1d2b} + +/^\p{Common}/8 + \x{589} + 0: \x{589} + \x{60c} + 0: \x{60c} + \x{61f} + 0: \x{61f} + \x{964} + 0: \x{964} + \x{965} + 0: \x{965} + \x{970} + 0: \x{970} + +/^\p{Inherited}/8 + \x{64b} + 0: \x{64b} + \x{654} + 0: \x{654} + \x{655} + 0: \x{655} + \x{200c} + 0: \x{200c} + ** Failers +No match + \x{64a} +No match + \x{656} +No match + +/^\p{Shavian}/8 + \x{10450} + 0: \x{10450} + \x{1047f} + 0: \x{1047f} + +/^\p{Deseret}/8 + \x{10400} + 0: \x{10400} + \x{1044f} + 0: \x{1044f} + +/^\p{Osmanya}/8 + \x{10480} + 0: \x{10480} + \x{1049d} + 0: \x{1049d} + \x{104a0} + 0: \x{104a0} + \x{104a9} + 0: \x{104a9} + ** Failers +No match + \x{1049e} +No match + \x{1049f} +No match + \x{104aa} +No match + +/\p{Zl}{2,3}+/8BZ +------------------------------------------------------------------ + Bra + prop Zl {2} + prop Zl ?+ + Ket + End +------------------------------------------------------------------ + \xe2\x80\xa8\xe2\x80\xa8 + 0: \x{2028}\x{2028} + \x{2028}\x{2028}\x{2028} + 0: \x{2028}\x{2028}\x{2028} + +/\p{Zl}/8BZ +------------------------------------------------------------------ + Bra + prop Zl + Ket + End +------------------------------------------------------------------ + +/\p{Lu}{3}+/8BZ +------------------------------------------------------------------ + Bra + prop Lu {3} + Ket + End +------------------------------------------------------------------ + +/\pL{2}+/8BZ +------------------------------------------------------------------ + Bra + prop L {2} + Ket + End +------------------------------------------------------------------ + +/\p{Cc}{2}+/8BZ +------------------------------------------------------------------ + Bra + prop Cc {2} + Ket + End +------------------------------------------------------------------ + +/\x{c0}+\x{116}+/8i + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + +/[\x{c0}\x{116}]+/8i + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + +/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8 + \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}==== + 0: \x{102a4}\x{aa52}\x{a91d}\x{1c46}\x{10283}\x{1092e}\x{1c6b}\x{a93b}\x{a8bf}\x{1ba0}\x{a50a} + +/\x{a77d}\x{1d79}/8i + \x{a77d}\x{1d79} + 0: \x{a77d}\x{1d79} + \x{1d79}\x{a77d} + 0: \x{1d79}\x{a77d} + +/\x{a77d}\x{1d79}/8 + \x{a77d}\x{1d79} + 0: \x{a77d}\x{1d79} + ** Failers +No match + \x{1d79}\x{a77d} +No match + +/(A)\1/8i + AA + 0: AA + 1: A + Aa + 0: Aa + 1: A + aa + 0: aa + 1: a + aA + 0: aA + 1: a + +/(\x{de})\1/8i + \x{de}\x{de} + 0: \x{de}\x{de} + 1: \x{de} + \x{de}\x{fe} + 0: \x{de}\x{fe} + 1: \x{de} + \x{fe}\x{fe} + 0: \x{fe}\x{fe} + 1: \x{fe} + \x{fe}\x{de} + 0: \x{fe}\x{de} + 1: \x{fe} + +/(\x{10a})\1/8i + \x{10a}\x{10a} + 0: \x{10a}\x{10a} + 1: \x{10a} + \x{10a}\x{10b} + 0: \x{10a}\x{10b} + 1: \x{10a} + \x{10b}\x{10b} + 0: \x{10b}\x{10b} + 1: \x{10b} + \x{10b}\x{10a} + 0: \x{10b}\x{10a} + 1: \x{10b} + +/The next two tests are for property support in non-UTF-8 mode/ + +/(?:\p{Lu}|\x20)+/ + \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59 + 0: A P\xc2T\xc9 TODAY + +/[\p{Lu}\x20]+/ + \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59 + 0: A P\xc2T\xc9 TODAY + / End of testinput6 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput7 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput7 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput7 Mon Jun 8 18:51:30 2009 @@ -2735,7 +2735,7 @@ No match /^a b -  c/x +  c/x abc 0: abc @@ -2973,7 +2973,7 @@ {4,5a}bc 0: {4,5a}bc -/^a.b/ +/^a.b/<lf> a\rb 0: a\x0db *** Failers @@ -3039,9 +3039,9 @@ abcdefghijk\12S 0: abcdefghijk\x0aS -/ab\gdef/ - abgdef - 0: abgdef +/ab\idef/ + abidef + 0: abidef /a{0}bc/ bc @@ -4573,8 +4573,6 @@ abq No match -/ab{1,}bc/ - /ab+bc/ abbbbc 0: abbbbc @@ -6600,7 +6598,7 @@ xyz\rabc\<lf> No match -/abc$/m +/abc$/m<lf> xyzabc 0: abc xyzabc\n @@ -6656,7 +6654,7 @@ xyz\rabcdef No match -/.*/ +/.*/<lf> abc\ndef 0: abc 1: ab @@ -6728,4 +6726,648 @@ abc\r\ndef 0: abc\x0d\x0adef +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + 0: abc=xyz\\x0apqr + 1: abc=xyz\\x0apq + 2: abc=xyz\\x0ap + 3: abc=xyz\\x0a + 4: abc=xyz\ + 5: abc=xyz + 6: abc=xy + 7: abc=x + 8: abc= + +/^(a()*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(?:a(?:(?:))*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(a()+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/^(?:a(?:(?:))+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/<lf> + a\rb + 0: a\x0db + a\nb\<cr> + 0: a\x0ab + ** Failers +No match + a\nb +No match + a\nb\<any> +No match + a\rb\<cr> +No match + a\rb\<any> +No match + +/^abc./mgx<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + +/abc.$/mgx<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc9 + +/^a\Rb/<bsr_unicode> + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/<bsr_unicode> + ab + 0: ab + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + +/^a\R+b/<bsr_unicode> + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + ** Failers +No match + ab +No match + +/^a\R{1,3}b/<bsr_unicode> + a\nb + 0: a\x0ab + a\n\rb + 0: a\x0a\x0db + a\n\r\x85b + 0: a\x0a\x0d\x85b + a\r\n\r\nb + 0: a\x0d\x0a\x0d\x0ab + a\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0ab + a\n\r\n\rb + 0: a\x0a\x0d\x0a\x0db + a\n\n\r\nb + 0: a\x0a\x0a\x0d\x0ab + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/^a[\R]b/<bsr_unicode> + aRb + 0: aRb + ** Failers +No match + a\nb +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \r\nfoo +No match + \nfoo +No match + +/.+foo/<crlf> + afoo + 0: afoo + \nfoo + 0: \x0afoo + ** Failers +No match + \r\nfoo +No match + +/.+foo/<any> + afoo + 0: afoo + ** Failers +No match + \nfoo +No match + \r\nfoo +No match + +/.+foo/s + afoo + 0: afoo + \r\nfoo + 0: \x0d\x0afoo + \nfoo + 0: \x0afoo + +/^$/mg<any> + abc\r\rxyz + 0: + abc\n\rxyz + 0: + ** Failers +No match + abc\r\nxyz +No match + +/^X/m + XABC + 0: X + ** Failers +No match + XABC\B +No match + +/(?m)^$/<any>g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + +/(?m)^$|^\r\n/<any>g+ + abc\r\n\r\n + 0: \x0d\x0a + 0+ + 1: + +/(?m)$/<any>g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a\x0d\x0a + 0: + 0+ \x0d\x0a + 0: + 0+ + +/(?|(abc)|(xyz))/ + >abc< + 0: abc + >xyz< + 0: xyz + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + 0: xabcx + xxyzx + 0: xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + 0: xabcpqrx + xxyzx + 0: xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + 0: abcabc + xyzabc + 0: xyzabc + ** Failers +No match + xyzxyz +No match + +/\H\h\V\v/ + X X\x0a + 0: X X\x0a + X\x09X\x0b + 0: X\x09X\x0b + ** Failers +No match + \xa0 X\x0a +No match + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0X\x0a\x0b\x0c\x0d + 1: \x09 \xa0X\x0a\x0b\x0c + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0\x0a\x0b\x0c\x0d + 1: \x09 \xa0\x0a\x0b\x0c + \x09\x20\xa0\x0a\x0b\x0c + 0: \x09 \xa0\x0a\x0b\x0c + ** Failers +No match + \x09\x20\xa0\x0a\x0b +No match + +/\H{3,4}/ + XY ABCDE + 0: ABCD + 1: ABC + XY PQR ST + 0: PQR + +/.\h{3,4}./ + XY AB PQRS + 0: B P + 1: B + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + 0: XNNNYZ + > X NYQZ + 0: X NYQZ + ** Failers +No match + >XYZ +No match + > X NY Z +No match + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + 0: XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/<crlf> + \r\nA +No match + +/\nA/<crlf> + \r\nA + 0: \x0aA + +/[\r\n]A/<crlf> + \r\nA + 0: \x0aA + +/(\r|\n)A/<crlf> + \r\nA + 0: \x0aA + +/a\Rb/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R{2,4}b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I<bsr_unicode> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\<bsr_anycrlf> +No match + a\x0b\0bb\<bsr_anycrlf> +No match + +/a(?!)|\wbc/ + abc + 0: abc + +/a[]b/<JS> + ** Failers +No match + ab +No match + +/a[]+b/<JS> + ** Failers +No match + ab +No match + +/a[]*+b/<JS> + ** Failers +No match + ab +No match + +/a[^]b/<JS> + aXb + 0: aXb + a\nb + 0: a\x0ab + ** Failers +No match + ab +No match + +/a[^]+b/<JS> + aXb + 0: aXb + a\nX\nXb + 0: a\x0aX\x0aXb + ** Failers +No match + ab +No match + +/X$/E + X + 0: X + ** Failers +No match + X\n +No match + +/X$/ + X + 0: X + X\n + 0: X + +/xyz/C + xyz +--->xyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz +--->abcxyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz\Y +--->abcxyz + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + ** Failers +No match + abc +No match + abc\Y +--->abc + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + abcxypqr +No match + abcxypqr\Y +--->abcxypqr + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + +/(?C)ab/ + ab +--->ab + 0 ^ a + 0: ab + \C-ab + 0: ab + +/ab/C + ab +--->ab + +0 ^ a + +1 ^^ b + +2 ^ ^ + 0: ab + \C-ab + 0: ab + +/^"((?(?=[a])[^"])|b)*"$/C + "ab" +--->"ab" + +0 ^ ^ + +1 ^ " + +2 ^^ ((?(?=[a])[^"])|b)* ++21 ^^ " + +3 ^^ (?(?=[a])[^"]) ++18 ^^ b + +5 ^^ (?=[a]) + +8 ^ [a] ++11 ^^ ) ++12 ^^ [^"] ++16 ^ ^ ) ++17 ^ ^ | ++21 ^ ^ " + +3 ^ ^ (?(?=[a])[^"]) ++18 ^ ^ b + +5 ^ ^ (?=[a]) + +8 ^ [a] ++19 ^ ^ ) ++21 ^ ^ " + +3 ^ ^ (?(?=[a])[^"]) ++18 ^ ^ b + +5 ^ ^ (?=[a]) + +8 ^ [a] ++17 ^ ^ | ++22 ^ ^ $ ++23 ^ ^ + 0: "ab" + \C-"ab" + 0: "ab" + / End of testinput7 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput8 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput8 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput8 Mon Jun 8 18:51:30 2009 @@ -1028,4 +1028,264 @@ \x{85} 0: \x{85} +/^abc./mgx8<any> + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/mgx8<any> + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/8<bsr_unicode> + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/8<bsr_unicode> + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + +/\V?\v{3,4}/8 + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: X\x{0a}\x{0b}\x{0c}\x{0d} + 1: X\x{0a}\x{0b}\x{0c} + +/\h+\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a} + +/\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: X\x{0a}\x{0a}\x{0a} + +/\H\h\V\v/8 + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + 1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + 1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/a\Rb/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/X/8f<any> + A\x{1ec5}ABCXYZ + 0: X + / End of testinput 8 / Modified: freeswitch/trunk/libs/pcre/testdata/testoutput9 ============================================================================== --- freeswitch/trunk/libs/pcre/testdata/testoutput9 (original) +++ freeswitch/trunk/libs/pcre/testdata/testoutput9 Mon Jun 8 18:51:30 2009 @@ -271,7 +271,7 @@ No match /^\p{Cs}/8 - \x{dfff} + \?\x{dfff} 0: \x{dfff} ** Failers No match @@ -285,7 +285,7 @@ No match Z No match - \x{dfff} + \x{e000} No match /^\p{Lm}/8 @@ -1624,4 +1624,50 @@ AXY No match +/^\x{023a}+?(\x{0130}+)/8i + \x{023a}\x{2c65}\x{0130} + 0: \x{23a}\x{2c65}\x{130} + +/^\x{023a}+([^X])/8i + \x{023a}\x{2c65}X + 0: \x{23a}\x{2c65} + +/\x{c0}+\x{116}+/8i + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + 1: \x{c0}\x{e0}\x{116} + +/[\x{c0}\x{116}]+/8i + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + 1: \x{c0}\x{e0}\x{116} + 2: \x{c0}\x{e0} + 3: \x{c0} + +/Check property support in non-UTF-8 mode/ + +/\p{L}{4}/ + 123abcdefg + 0: abcd + 123abc\xc4\xc5zz + 0: abc\xc4 + +/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8 + \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}==== + 0: \x{102a4}\x{aa52}\x{a91d}\x{1c46}\x{10283}\x{1092e}\x{1c6b}\x{a93b}\x{a8bf}\x{1ba0}\x{a50a} + +/\x{a77d}\x{1d79}/8i + \x{a77d}\x{1d79} + 0: \x{a77d}\x{1d79} + \x{1d79}\x{a77d} + 0: \x{1d79}\x{a77d} + +/\x{a77d}\x{1d79}/8 + \x{a77d}\x{1d79} + 0: \x{a77d}\x{1d79} + ** Failers +No match + \x{1d79}\x{a77d} +No match + / End / Added: freeswitch/trunk/libs/pcre/testdata/wintestinput3 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/wintestinput3 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,91 @@ +/^[\w]+/ + *** Failers + �cole + +/^[\w]+/Lfrench + �cole + +/^[\w]+/ + *** Failers + �cole + +/^[\W]+/ + �cole + +/^[\W]+/Lfrench + *** Failers + �cole + +/[\b]/ + \b + *** Failers + a + +/[\b]/Lfrench + \b + *** Failers + a + +/^\w+/ + *** Failers + �cole + +/^\w+/Lfrench + �cole + +/(.+)\b(.+)/ + �cole + +/(.+)\b(.+)/Lfrench + *** Failers + �cole + +/�cole/i + �cole + *** Failers + �cole + +/�cole/iLfrench + �cole + �cole + +/\w/IS + +/\w/ISLfrench + +/^[\xc8-\xc9]/iLfrench + �cole + �cole + +/^[\xc8-\xc9]/Lfrench + �cole + *** Failers + �cole + +/\W+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[\W]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[^[:alpha:]]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/\w+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[\w]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench + +/ End of testinput3 / Added: freeswitch/trunk/libs/pcre/testdata/wintestoutput3 ============================================================================== --- (empty file) +++ freeswitch/trunk/libs/pcre/testdata/wintestoutput3 Mon Jun 8 18:51:30 2009 @@ -0,0 +1,164 @@ +/^[\w]+/ + *** Failers +No match + �cole +No match + +/^[\w]+/Lfrench + �cole + 0: �cole + +/^[\w]+/ + *** Failers +No match + �cole +No match + +/^[\W]+/ + �cole + 0: \xc9 + +/^[\W]+/Lfrench + *** Failers + 0: *** + �cole +No match + +/[\b]/ + \b + 0: \x08 + *** Failers +No match + a +No match + +/[\b]/Lfrench + \b + 0: \x08 + *** Failers +No match + a +No match + +/^\w+/ + *** Failers +No match + �cole +No match + +/^\w+/Lfrench + �cole + 0: �cole + +/(.+)\b(.+)/ + �cole + 0: \xc9cole + 1: \xc9 + 2: cole + +/(.+)\b(.+)/Lfrench + *** Failers + 0: *** Failers + 1: *** + 2: Failers + �cole +No match + +/�cole/i + �cole + 0: \xc9cole + *** Failers +No match + �cole +No match + +/�cole/iLfrench + �cole + 0: �cole + �cole + 0: �cole + +/\w/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + +/\w/ISLfrench +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � + � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � + � � + +/^[\xc8-\xc9]/iLfrench + �cole + 0: � + �cole + 0: � + +/^[\xc8-\xc9]/Lfrench + �cole + 0: � + *** Failers +No match + �cole +No match + +/\W+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[\W]+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[^[:alpha:]]+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/\w+/Lfrench + >>>\xaa<<< + 0: � + >>>\xba<<< + 0: � + +/[\w]+/Lfrench + >>>\xaa<<< + 0: � + >>>\xba<<< + 0: � + +/[[:alpha:]]+/Lfrench + >>>\xaa<<< + 0: � + >>>\xba<<< + 0: � + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench +------------------------------------------------------------------ + Bra + [A-Za-z\x83\x8a\x8c\x8e\x9a\x9c\x9e\x9f\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] + [a-z\x83\x9a\x9c\x9e\xaa\xb5\xba\xdf-\xf6\xf8-\xff] + [A-Z\x8a\x8c\x8e\x9f\xc0-\xd6\xd8-\xde] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/ End of testinput3 / Modified: freeswitch/trunk/libs/pcre/ucp.h ============================================================================== --- freeswitch/trunk/libs/pcre/ucp.h (original) +++ freeswitch/trunk/libs/pcre/ucp.h Mon Jun 8 18:51:30 2009 @@ -6,7 +6,8 @@ #define _UCP_H /* This file contains definitions of the property values that are returned by -the function _pcre_ucp_findprop(). */ +the UCD access macros. New values that are added for new releases of Unicode +should always be at the end of each enum, for backwards compatibility. */ /* These are the general character categories. */ @@ -118,7 +119,25 @@ ucp_Tibetan, ucp_Tifinagh, ucp_Ugaritic, - ucp_Yi + ucp_Yi, + /* New for Unicode 5.0: */ + ucp_Balinese, + ucp_Cuneiform, + ucp_Nko, + ucp_Phags_Pa, + ucp_Phoenician, + /* New for Unicode 5.1: */ + ucp_Carian, + ucp_Cham, + ucp_Kayah_Li, + ucp_Lepcha, + ucp_Lycian, + ucp_Lydian, + ucp_Ol_Chiki, + ucp_Rejang, + ucp_Saurashtra, + ucp_Sundanese, + ucp_Vai }; #endif